© 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. 75902
    Prev
    Next
    INDEX
    Explanations

    Jean Marais, Manhid, Manabendra

    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
    یریت
    -0.77
    Enc
    -0.75
    obsc
    -0.73
    謁
    -0.73
     Enc
    -0.72
    镁
    -0.71
    bảng
    -0.70
    gamer
    -0.70
    <bos>
    -0.70
    što
    -0.69
    POSITIVE LOGITS
    unut
    0.90
    mulo
    0.84
    Writer
    0.79
    ificato
    0.79
    ardez
    0.77
     imat
    0.76
     psychiatry
    0.76
    CION
    0.76
    bben
    0.75
    jeron
    0.75
    Activations Density 0.000%

    No Known Activations