© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38726
    Prev
    Next
    INDEX
    Explanations

    cover a range of

    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
    \
    -2.08
    }
    -1.96
    ↵↵
    -1.91
    '
    -1.73
     or
    -1.70
     more
    -1.66
    🎶
    -1.66
    </i>
    -1.64
    <b>
    -1.63
     as
    -1.63
    POSITIVE LOGITS
    苙
    2.16
    呿
    1.90
    歃
    1.88
    τερα
    1.88
     ouest
    1.84
    
    1.84
     entirety
    1.82
    งิน
    1.79
    pecabe
    1.78
    衚
    1.78
    Activations Density 0.038%

    No Known Activations