© 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. 16338
    Prev
    Next
    INDEX
    Explanations

    remove all

    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
    が可能
    -0.91
     サポート
    -0.87
    ˀ
    -0.86
    unjuk
    -0.85
     også
    -0.85
    lassification
    -0.83
    Salam
    -0.82
    vás
    -0.81
     նաև
    -0.81
    ällor
    -0.81
    POSITIVE LOGITS
     entire
    1.29
    全部
    1.27
    RemoveAll
    1.27
     deleteAll
    1.23
     all
    1.23
     Wszyst
    1.20
    ulfon
    1.19
     removeAll
    1.16
    全都
    1.10
    清空
    1.09
    Activations Density 0.012%

    No Known Activations