© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15468
    Prev
    Next
    INDEX
    Explanations

    What to do

    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
    ↵↵
    -2.44
     a
    -2.03
     what
    -1.73
    珦
    -1.67
     on
    -1.63
     oblasti
    -1.57
     In
    -1.55
     of
    -1.53
     füh
    -1.52
    ⚌
    -1.52
    POSITIVE LOGITS
    7
    2.13
    9
    2.06
    8
    1.96
    2
    1.84
    4
    1.80
    ness
    1.77
    s
    1.77
    鬭
    1.74
    6
    1.74
    transQ
    1.74
    Activations Density 0.000%

    No Known Activations