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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16167
    Prev
    Next
    INDEX
    Explanations

    numbers in code or lists

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

    The neuron is detecting numerical tokens that contain a decimal point (i.e., floating-point numbers).

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

    the word "by" when it indicates authorship or attribution.

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

    mentions of years written as four-digit numbers (e.g., calendar years).

    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_24_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
    竰
    0.77
     επα
    0.72
     режи
    0.71
     lí
    0.70
     boul
    0.70
    𝑽
    0.70
     〢
    0.69
     ற
    0.68
     ತೋ
    0.68
    攽
    0.68
    POSITIVE LOGITS
    '
    1.03
    ’
    0.91
    1
    0.89
    2
    0.89
    lung
    0.84
    long
    0.83
    3
    0.83
    8
    0.83
    snap
    0.82
    sun
    0.81
    Activations Density 0.000%

    No Known Activations