© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108257
    Prev
    Next
    INDEX
    Explanations

    trial court proceedings

    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
    '
    -1.00
    file
    -0.99
    itchfield
    -0.96
    bildung
    -0.94
    fälle
    -0.93
    wenn
    -0.93
     дет
    -0.92
    此时
    -0.88
     ‘‘
    -0.88
     sowie
    -0.87
    POSITIVE LOGITS
    ogue
    1.23
    ists
    1.11
    丈夫
    1.10
    istic
    1.03
    ISTS
    1.01
    ofthe
    0.98
     Hå
    0.93
    ability
    0.91
     écoulé
    0.91
     Alors
    0.90
    Activations Density 0.020%

    No Known Activations