© 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. 64236
    Prev
    Next
    INDEX
    Explanations

    java packages and dates

    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
    xiaomi
    -0.91
     but
    -0.85
    Balan
    -0.82
    Quali
    -0.81
    ₂,
    -0.79
    artisan
    -0.77
    Variations
    -0.76
    Gera
    -0.76
     tula
    -0.75
    airbnb
    -0.75
    POSITIVE LOGITS
    sun
    1.28
    fasterxml
    1.19
     sun
    1.16
    SUN
    1.16
    Sun
    1.07
     SUN
    1.03
    Example
    1.01
    ített
    0.98
    example
    0.98
    OPEN
    0.92
    Activations Density 0.004%

    No Known Activations