© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10002
    Prev
    Next
    INDEX
    Explanations

    mathematical numbers and types

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on standalone numeric tokens or number‐like codes (e.g. digits, measurements, tariff codes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numeric strings, particularly in technical, classificatory, or formal documentation contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of formal classification or categorization, such as assigning items to groups, codes, categories, or domains and ranges.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    다는
    0.52
    više
    0.52
    ić
    0.50
    吉祥
    0.50
    男朋友
    0.50
    IDTH
    0.50
     deportivo
    0.49
    AutoScaleMode
    0.49
     meu
    0.49
     aniversário
    0.48
    POSITIVE LOGITS
     integers
    1.05
    整数
    0.98
     সংখ্য
    0.91
     integer
    0.88
     اعداد
    0.80
    Numbers
    0.80
     Integer
    0.79
     Numbers
    0.79
     Zahlen
    0.77
    mathbb
    0.76
    Activations Density 0.021%

    No Known Activations