© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99915
    Prev
    Next
    INDEX
    Explanations

    legal case citations and numbers

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

    The neuron selectively activates on numeric tokens—both integers and decimal numbers—regardless of context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    を活用
    -1.55
    Ogni
    -1.51
    Ռ
    -1.49
    Répondre
    -1.48
    ónimo
    -1.43
    齶
    -1.42
    peut
    -1.42
    蚰
    -1.41
     gorro
    -1.41
    kami
    -1.39
    POSITIVE LOGITS
    :
    1.91
    on
    1.83
     are
    1.80
    in
    1.73
     is
    1.65
    en
    1.60
    In
    1.57
    with
    1.52
    On
    1.51
    as
    1.45
    Activations Density 0.281%

    No Known Activations