© 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. 13182
    Prev
    Next
    INDEX
    Explanations

    fictional, market, chocolate, nc

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

    The neuron activates on four-digit numeric tokens, i.e. year or year‐like number references.

    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
    Pem
    0.73
    저
    0.72
    По
    0.72
    Ком
    0.69
    Gen
    0.67
    두
    0.67
    마다
    0.66
    별
    0.66
    它
    0.66
    Я
    0.65
    POSITIVE LOGITS
    cional
    0.80
    gradle
    0.78
     інте
    0.77
    yw
    0.77
    人了
    0.76
     interi
    0.75
    <unused21>
    0.75
    schaft
    0.75
     remov
    0.73
    лению
    0.73
    Activations Density 0.000%

    No Known Activations