© 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. 10-GEMMASCOPE-RES-131K
    7. 123722
    Prev
    Next
    INDEX
    Explanations

    status, centrifugal, motivational

    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_10/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
    n
    -3.23
    d
    -2.95
    u
    -2.91
     \
    -2.72
     ;
    -2.70
     оценка
    -2.66
    н
    -2.59
     This
    -2.58
     was
    -2.55
    h
    -2.42
    POSITIVE LOGITS
    vantaged
    2.92
     boken
    2.84
    ました
    2.84
    坼
    2.78
    埽
    2.72
    تیجه
    2.72
     whoſe
    2.70
    殽
    2.70
     kacang
    2.67
    硨
    2.66
    Activations Density 0.005%

    No Known Activations