© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95623
    Prev
    Next
    INDEX
    Explanations

    starters like Q:, /*, or proper nouns

    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
     tendency
    -1.04
     again
    -1.03
    Preparación
    -0.93
     novamente
    -0.93
    órica
    -0.93
     operazioni
    -0.93
    ತ್ತು
    -0.93
    Elaboración
    -0.92
     when
    -0.91
     Again
    -0.89
    POSITIVE LOGITS
     ролях
    0.98
     革
    0.92
     米
    0.90
    rufen
    0.88
    фі
    0.86
     отеля
    0.84
    CALL
    0.83
    onsors
    0.80
     Lup
    0.80
     auspices
    0.80
    Activations Density 0.000%

    No Known Activations