© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15860
    Prev
    Next
    INDEX
    Explanations

    `title` attribute

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

    The neuron is triggered by numeric or quantitative expressions—numbers, measurements, statistics, prices, vote counts, times, etc.

    oai_token-act-pair · o4-miniTriggered 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
     तुम्ही
    0.56
    Chứng
    0.55
     അതി
    0.49
     ventre
    0.48
    Minus
    0.48
    얹
    0.48
    राई
    0.47
    ሆ
    0.47
    参照
    0.46
     शख
    0.46
    POSITIVE LOGITS
    ISION
    0.55
    zado
    0.53
     פור
    0.53
     PREC
    0.52
    uegos
    0.51
    ปรับ
    0.51
    ificados
    0.51
     Parque
    0.50
     effluent
    0.50
     Oxidation
    0.49
    Activations Density 0.007%

    No Known Activations