© 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. 24-GEMMASCOPE-2-RES-16K
    4. 15900
    Prev
    Next
    INDEX
    Explanations

    compare function

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

    The neuron primarily detects numeric tokens and number-like expressions (e.g., years, quantities, days of the week with numbers, decimal values).

    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_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
    es
    1.05
    er
    1.01
    e
    0.97
    ss
    0.96
    et
    0.94
    st
    0.94
    sp
    0.91
    id
    0.89
    ul
    0.89
    n
    0.89
    POSITIVE LOGITS
    があり
    0.97
    㫴
    0.93
     abelian
    0.92
     Abelian
    0.91
    ChessBot
    0.90
     semicon
    0.88
    ждению
    0.87
    ены
    0.86
    푎
    0.86
     previewBuilder
    0.85
    Activations Density 0.000%

    No Known Activations