© 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. 34-GEMMASCOPE-RES-131K
    7. 98806
    Prev
    Next
    INDEX
    Explanations

    cors, cos, cros, cause, corinth

    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_34/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
     дете
    -0.80
     precon
    -0.79
     skin
    -0.78
    searchResult
    -0.77
    Protos
    -0.77
     occipital
    -0.75
    squirrel
    -0.73
    recor
    -0.72
    zzleHttp
    -0.71
     Skin
    -0.70
    POSITIVE LOGITS
    Cors
    1.14
     Cors
    0.92
     cors
    0.83
     Corsica
    0.77
    play
    0.75
     Corso
    0.73
     IBM
    0.72
     play
    0.71
    سیون
    0.71
    IBM
    0.70
    Activations Density 0.035%

    No Known Activations