© 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. 129841
    Prev
    Next
    INDEX
    Explanations

    recalling, suspension, sell, created

    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
     nossa
    -1.02
    tituts
    -0.98
    кипа
    -0.97
     combatants
    -0.96
     μας
    -0.96
     апте
    -0.94
    Herkunft
    -0.94
    ֺ
    -0.94
     we
    -0.93
    सन्दर्भ
    -0.92
    POSITIVE LOGITS
     “
    1.56
     "
    1.49
     "[
    1.31
     “[
    1.27
     “(
    1.27
     listed
    1.23
     "(
    1.20
     monasterio
    1.13
     Schreiben
    1.12
    德國
    1.09
    Activations Density 0.064%

    No Known Activations