© 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. 22-GEMMASCOPE-RES-131K
    7. 130230
    Prev
    Next
    INDEX
    Explanations

    San Francisco

    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_22/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
    пит
    -1.07
     bara
    -0.99
    uksessa
    -0.98
     INSTRUMENTS
    -0.96
     voir
    -0.95
    歓
    -0.94
     justa
    -0.94
     ترت
    -0.92
     RECORDS
    -0.91
    áty
    -0.91
    POSITIVE LOGITS
     nových
    1.06
     improved
    1.05
     Répondre
    1.02
     nový
    1.01
     renewed
    1.00
     těch
    1.00
     bringing
    0.99
     nového
    0.97
     illiterate
    0.96
    Posté
    0.96
    Activations Density 0.008%

    No Known Activations