© 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. 38657
    Prev
    Next
    INDEX
    Explanations

    Indian names

    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>
    -2.14
    u
    -1.95
     we
    -1.84
    -
    -1.80
     Réalisation
    -1.77
    i
    -1.74
    self
    -1.70
    It
    -1.69
    it
    -1.67
    you
    -1.63
    POSITIVE LOGITS
    </h3>
    2.05
    蛻
    1.91
    AdvEx
    1.91
    MenuInflater
    1.85
    鮠
    1.84
    ées
    1.84
    дәбият
    1.83
    
    1.80
    ksamkeit
    1.78
    咘
    1.78
    Activations Density 0.008%

    No Known Activations