© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6669
    Prev
    Next
    INDEX
    Explanations

    business and tech abbreviations

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

    The neuron fires strongly on numeric tokens appearing in parentheses, i.e. parenthesized numbers (like “(1)”, “(75)”, 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_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
    )
    0.81
    -
    0.80
    _
    0.78
    ’
    0.71
    sthe
    0.70
    st
    0.68
    C
    0.66
    ),
    0.65
     also
    0.65
    Name
    0.64
    POSITIVE LOGITS
    <unused416>
    0.76
    맇
    0.75
     👀
    0.74
    <unused667>
    0.73
    많은
    0.72
     ପ
    0.72
    <unused2146>
    0.71
    рачи
    0.71
    躏
    0.71
    <unused298>
    0.71
    Activations Density 0.012%

    No Known Activations