© 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. 34227
    Prev
    Next
    INDEX
    Explanations

    data structures and classifications

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

    The neuron activates on numeric tokens (e.g. standalone numbers or digits).

    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
    ဿ
    -0.91
     bringe
    -0.91
    Premios
    -0.90
    avelength
    -0.86
     barva
    -0.85
     メッセージ
    -0.84
     RAILROAD
    -0.84
    möbel
    -0.82
    Moi
    -0.82
    Комментарий
    -0.82
    POSITIVE LOGITS
     overall
    0.82
     Chief
    0.79
     entry
    0.78
     name
    0.77
    全部
    0.75
    +
    0.75
     يأ
    0.75
    overall
    0.74
    ブー
    0.74
     articol
    0.73
    Activations Density 0.014%

    No Known Activations