© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 67418
    Prev
    Next
    INDEX
    Explanations

    time, punctuation, or word completions

    np_acts-logits-general · gemini-2.5-flash-lite

    orbuilding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    त्सा
    0.51
    ேட்
    0.50
     المتوسط
    0.48
     mínimo
    0.48
    štění
    0.46
    Modelo
    0.46
     accidentes
    0.46
    䯩
    0.46
    भाग
    0.45
     окончания
    0.45
    POSITIVE LOGITS
    </u>
    0.56
    {
    0.55
    </strong>
    0.52
    </em>
    0.51
    <0x0D>
    0.50
    {'
    0.47
    パフォーマンス
    0.47
    </b>
    0.47
     {
    0.46
    0.46
    Activations Density 0.001%

    No Known Activations