© 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. 70784
    Prev
    Next
    INDEX
    Explanations

    keys and values

    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
    recuper
    -0.81
     plus
    -0.78
    "!
    -0.76
     exactly
    -0.75
    ).
    -0.75
     increase
    -0.73
     upwards
    -0.73
     wants
    -0.73
    ↵↵↵↵
    -0.72
     Landfill
    -0.72
    POSITIVE LOGITS
     {},
    0.89
    pezif
    0.89
     TRUST
    0.89
     Moroccan
    0.85
     الاف
    0.84
    uels
    0.83
     iPod
    0.82
    quart
    0.82
     polícia
    0.82
     '',
    0.82
    Activations Density 0.064%

    No Known Activations