© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39116
    Prev
    Next
    INDEX
    Explanations

    Q: and Pages

    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_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
     даже
    -1.07
    例子
    -0.93
    cioc
    -0.89
    ネーム
    -0.89
    стри
    -0.88
    눕
    -0.88
    عين
    -0.86
    リスト
    -0.86
     навіть
    -0.86
     automne
    -0.85
    POSITIVE LOGITS
    funeralhome
    0.88
    chang
    0.84
     prawo
    0.81
     soft
    0.80
    CHANGES
    0.79
     been
    0.79
    both
    0.78
    lemmer
    0.78
     richtig
    0.78
    borderBottom
    0.78
    Activations Density 0.001%

    No Known Activations