© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81375
    Prev
    Next
    INDEX
    Explanations

    arrow functions

    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_34/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
     ngunit
    -0.88
     adulta
    -0.86
    潟
    -0.85
     даже
    -0.85
    dima
    -0.84
     corrom
    -0.82
     الفصل
    -0.82
    只是
    -0.80
    chila
    -0.79
    ógio
    -0.79
    POSITIVE LOGITS
     =>
    1.55
     that
    0.98
    =>
    0.97
    、『
    0.92
    "],
    0.91
    "];
    0.87
    象徴
    0.86
     dunque
    0.85
    »,
    0.85
    ,</
    0.84
    Activations Density 0.003%

    No Known Activations