© 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. 34-GEMMASCOPE-RES-131K
    7. 117665
    Prev
    Next
    INDEX
    Explanations

    document structure and review sections

    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
    Mutual
    -0.77
     sunt
    -0.75
    seless
    -0.75
    oł
    -0.75
    onDelete
    -0.75
    彼此
    -0.73
     Advertising
    -0.73
     mutual
    -0.72
     Mutual
    -0.72
    踱
    -0.71
    POSITIVE LOGITS
     Dorsal
    0.87
    երի
    0.84
    <h3>
    0.84
    يئة
    0.80
    纣
    0.79
    观的
    0.79
     accél
    0.79
    ئات
    0.78
    当前
    0.78
    ませんか
    0.78
    Activations Density 0.002%

    No Known Activations