© 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. 11762
    Prev
    Next
    INDEX
    Explanations

    congressional and California

    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
    鏖
    -0.87
    ;->
    -0.79
    不良
    -0.77
    ằm
    -0.74
    ajoz
    -0.73
    нутрен
    -0.73
     být
    -0.70
    GC
    -0.70
    j
    -0.70
     тик
    -0.69
    POSITIVE LOGITS
    ulsive
    0.87
     BUTTER
    0.78
    CALIFORNIA
    0.77
     Valentin
    0.77
    Valentin
    0.76
    רט
    0.75
     studenten
    0.75
     CRITERIA
    0.74
    crush
    0.74
    enumii
    0.74
    Activations Density 0.005%

    No Known Activations