© 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. 129327
    Prev
    Next
    INDEX
    Explanations

    dates and days of the week

    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
     because
    -2.11
     hoga
    -1.84
     during
    -1.84
     there
    -1.83
     pablo
    -1.79
     until
    -1.77
     wijze
    -1.73
     mami
    -1.72
    νες
    -1.70
    There
    -1.70
    POSITIVE LOGITS
    </b>
    2.25
     území
    1.79
    useNewUrlParser
    1.77
    聍
    1.72
    流れる
    1.63
     altında
    1.63
     srebr
    1.60
    </sup>
    1.59
     ayrıca
    1.54
     cumbre
    1.52
    Activations Density 0.046%

    No Known Activations