© 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. 21066
    Prev
    Next
    INDEX
    Explanations

    programming init function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    雱
    -2.61
    “
    -2.39
    勦
    -2.36
     

    -2.36
    er
    -2.33
     периода
    -2.31
    鬭
    -2.31
     analogy
    -2.22
    and
    -2.20
     работают
    -2.20
    POSITIVE LOGITS
    メリカ
    2.95
    塲
    2.75
    媖
    2.70
    柃
    2.67
    しちゃ
    2.64
    ﹊
    2.63
    ㊦
    2.63
    镚
    2.61
    杙
    2.59
     ſou
    2.58
    Activations Density 0.030%

    No Known Activations