© 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. 70073
    Prev
    Next
    INDEX
    Explanations

    code 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
     parfü
    -1.79
     jú
    -1.73
     parfüm
    -1.72
    ※※
    -1.67
    ●●
    -1.66
     rokok
    -1.63
    ◆◆
    -1.60
     rése
    -1.58
     imprimé
    -1.57
    @@@@@
    -1.52
    POSITIVE LOGITS
     -
    2.17
     still
    1.91
     also
    1.77
     eventually
    1.69
     this
    1.56
     ultimately
    1.55
    </h2>
    1.55
     or
    1.48
     continue
    1.47
     subsequently
    1.45
    Activations Density 0.066%

    No Known Activations