© 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. 113856
    Prev
    Next
    INDEX
    Explanations

    accomplishments and feats

    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
    ೣ
    -1.63
    趼
    -1.57
     Fußballspieler
    -1.56
    
    -1.55
    ⢅
    -1.55
    </tfoot>
    -1.54
     nauki
    -1.49
     stroom
    -1.49
    鍬
    -1.43
    decoración
    -1.42
    POSITIVE LOGITS
     feats
    1.85
    Also
    1.75
    Like
    1.74
    Although
    1.66
     it
    1.63
    s
    1.63
    It
    1.61
    4
    1.61
    So
    1.60
    Another
    1.59
    Activations Density 0.018%

    No Known Activations