© 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. 58186
    Prev
    Next
    INDEX
    Explanations

    sharpness and its uses

    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
    Negative Logits
    {
    -2.58
    珢
    -2.09
     manter
    -1.95
     dichas
    -1.84
     acceptable
    -1.82
    埛
    -1.70
     stalled
    -1.66
     haja
    -1.65
    ⢊
    -1.64
     Añade
    -1.63
    POSITIVE LOGITS
    AdvEx
    1.95
     tarvit
    1.92
    棡
    1.88
    6
    1.84
     avaient
    1.81
     kaksi
    1.77
    st
    1.74
    というわけで
    1.73
     είναι
    1.68
    っていう
    1.66
    Activations Density 0.016%

    No Known Activations