© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127689
    Prev
    Next
    INDEX
    Explanations

    absolute quality intensifiers

    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
    雱
    -2.83
    撄
    -2.75
    
    -2.70
     dismal
    -2.66
     unſ
    -2.66
    ￪
    -2.64
     interesses
    -2.64
    棡
    -2.59
    蚡
    -2.58
    acterísticas
    -2.52
    POSITIVE LOGITS
    ↵
    4.63
    F
    3.52
    V
    3.42
    S
    3.33
    B
    3.27
    E
    3.25
    P
    3.03
    er
    3.00
    R
    3.00
     burgeoning
    2.89
    Activations Density 0.003%

    No Known Activations