© 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. 108176
    Prev
    Next
    INDEX
    Explanations

    java code and license terms

    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
    baño
    -0.79
     violin
    -0.77
    萬
    -0.76
    alling
    -0.73
    slf
    -0.70
     Romania
    -0.69
    koma
    -0.69
    zmir
    -0.68
     Medicaid
    -0.68
    ogra
    -0.67
    POSITIVE LOGITS
    Sun
    0.96
    sun
    0.93
     Sun
    0.92
    '{
    0.86
    Security
    0.85
    nością
    0.85
     SUN
    0.84
    SUN
    0.84
     dificultad
    0.82
    '(
    0.81
    Activations Density 0.073%

    No Known Activations