© 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. 84121
    Prev
    Next
    INDEX
    Explanations

    "mar" followed by words like "riages" or "healthy" after "Eating", "cognitive" after "A", code snippets, or names

    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
     all
    -1.08
     forfatter
    -1.08
     ΤΟ
    -1.08
    bedded
    -1.02
    合せ
    -0.99
    digitalWrite
    -0.99
     judicia
    -0.99
    #*
    -0.99
     since
    -0.97
    tifications
    -0.97
    POSITIVE LOGITS
     arşivlendi
    1.09
     इन
    1.06
     varietà
    1.06
    stination
    1.06
     defunct
    1.02
     propo
    1.02
     glared
    1.01
    Elin
    1.01
    ündigung
    1.01
     eventuell
    0.99
    Activations Density 0.000%

    No Known Activations