© 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. 22-GEMMASCOPE-RES-131K
    7. 34295
    Prev
    Next
    INDEX
    Explanations

    key-value assignments

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

    The neuron flags occurrences of numeric literals (tokens containing digits) in the code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    為に
    -2.27
    に入れる
    -1.99
     maniere
    -1.89
    ところに
    -1.88
    凄く
    -1.80
    裥
    -1.78
    っているので
    -1.77
    ⸱
    -1.77
    あぁ
    -1.77
    あー
    -1.77
    POSITIVE LOGITS
    は
    2.30
     is
    2.27
     in
    2.25
    を
    2.09
     just
    1.91
     was
    1.88
    が
    1.88
     =
    1.83
     are
    1.80
     so
    1.78
    Activations Density 0.004%

    No Known Activations