© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37961
    Prev
    Next
    INDEX
    Explanations

    from the, deep brush, Complex phosphorus, Blunted, PM2PM, The Cincinnati

    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
     scholarship
    -0.80
    netz
    -0.74
    หวัด
    -0.73
    olato
    -0.73
     sewed
    -0.72
     histamine
    -0.72
     MCP
    -0.71
     kereszt
    -0.71
     Bakan
    -0.70
     realizarse
    -0.70
    POSITIVE LOGITS
     penalty
    0.97
    lief
    0.91
     alivio
    0.84
     stance
    0.79
     penalties
    0.78
     movable
    0.78
     relief
    0.76
     ball
    0.76
     Samaritan
    0.76
     inflater
    0.76
    Activations Density 0.010%

    No Known Activations