© 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. 68388
    Prev
    Next
    INDEX
    Explanations

    overhaul, revamp, rebuild, improve

    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
    鬭
    -2.27
    下巴
    -2.25
    mpagne
    -2.25
    腘
    -2.23
     możesz
    -2.22
     precludes
    -2.22
     induces
    -2.19
     stirs
    -2.16
     hará
    -2.13
     můžete
    -2.11
    POSITIVE LOGITS
    𓆜
    2.80
    
    2.73
    .'”
    2.33
    𓆟
    2.25
    LY
    2.22
    誉
    2.13
     overhaul
    2.13
    媜
    2.09
     haupts
    2.06
    r
    2.05
    Activations Density 0.001%

    No Known Activations