© 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. 10-GEMMASCOPE-RES-131K
    7. 15339
    Prev
    Next
    INDEX
    Explanations

    towns, courts, and police

    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_10/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
    随后
    -1.09
     ”
    -1.05
    êncio
    -1.02
    юре
    -0.98
    </strong>
    -0.98
     europé
    -0.98
    fiés
    -0.97
     Olímpicos
    -0.96
    vieve
    -0.95
    økt
    -0.94
    POSITIVE LOGITS
    (
    1.06
     when
    1.01
     said
    0.99
     autorisés
    0.99
    ılmaz
    0.97
     one
    0.94
     that
    0.92
     validés
    0.91
     workshop
    0.90
    炷
    0.90
    Activations Density 0.090%

    No Known Activations