© 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. 68391
    Prev
    Next
    INDEX
    Explanations

    made in punjab tv

    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
    </b>
    -2.02
     hundred
    -1.96
    最后由
    -1.80
     thirteen
    -1.77
     fourteen
    -1.70
     any
    -1.69
    晅
    -1.69
     surprisingly
    -1.66
     thoughtful
    -1.65
     seventeen
    -1.65
    POSITIVE LOGITS
    轳
    2.33
    ༀ
    2.06
    antly
    2.02
    桄
    1.85
    ଃ
    1.80
    
    1.80
    genodigd
    1.80
    鼇
    1.78
    苤
    1.77
     bekom
    1.73
    Activations Density 0.000%

    No Known Activations