© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13021
    Prev
    Next
    INDEX
    Explanations

    Punctuation and symbols

    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
     one
    -1.72
     trouvez
    -1.54
    .
    -1.48
    ,
    -1.46
     TWO
    -1.45
    ၂
    -1.45
     Two
    -1.44
    If
    -1.42
     voyez
    -1.42
     حاول
    -1.34
    POSITIVE LOGITS
     protože
    1.95
     ponieważ
    1.83
     they
    1.83
     pretože
    1.79
    </h3>
    1.66
    有很多
    1.63
    然后
    1.63
     affitto
    1.58
    苼
    1.52
     have
    1.49
    Activations Density 0.057%

    No Known Activations