© 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. 107200
    Prev
    Next
    INDEX
    Explanations

    scope or limits

    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
     numerous
    -0.95
     more
    -0.91
     many
    -0.90
    ведена
    -0.89
     permesso
    -0.89
     murni
    -0.84
     messo
    -0.81
     thoughtful
    -0.81
    ঈ
    -0.80
     dozens
    -0.80
    POSITIVE LOGITS
    scope
    1.00
    migrationBuilder
    0.89
    iacute
    0.89
    Phase
    0.88
    Scope
    0.87
     scope
    0.85
    Strip
    0.84
    volves
    0.84
    </tr>
    0.82
    Ii
    0.81
    Activations Density 0.000%

    No Known Activations