© 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. 22549
    Prev
    Next
    INDEX
    Explanations

    holster, sheath, weapon, region

    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
    菝
    -2.39
    锜
    -2.30
     réfugi
    -2.14
    踅
    -2.02
    ///////////////
    -1.99
    o
    -1.98
    荭
    -1.88
    //////////////
    -1.85
    袛
    -1.85
     fanno
    -1.80
    POSITIVE LOGITS
    ↵
    2.22
    鋱
    2.00
     function
    1.80
    面白い
    1.80
    .”
    1.76
    5
    1.72
    8
    1.70
    卺
    1.68
     mieten
    1.66
    with
    1.63
    Activations Density 0.004%

    No Known Activations