© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65457
    Prev
    Next
    INDEX
    Explanations

    book club

    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
    Valve
    -0.85
    ⏩
    -0.85
     INEC
    -0.83
     Godfather
    -0.83
     solvable
    -0.83
     体育
    -0.79
     Proverbs
    -0.79
     Maxine
    -0.78
     uniques
    -0.77
    ловой
    -0.76
    POSITIVE LOGITS
     club
    2.44
    club
    2.25
     Club
    2.05
     CLUB
    1.92
     clubs
    1.83
    Club
    1.78
     clube
    1.60
    CLUB
    1.52
     clubes
    1.48
     selection
    1.47
    Activations Density 0.037%

    No Known Activations