© 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. 241
    Prev
    Next
    INDEX
    Explanations

    recurring motifs or siblings

    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
     féri
    0.37
    ('${
    0.36
    Đ
    0.33
    ®
    0.32
    🏟
    0.32
    sync
    0.32
    ICT
    0.31
     ম্যাচে
    0.31
    OURCE
    0.31
     спорта
    0.31
    POSITIVE LOGITS
     Foreground
    0.39
     Value
    0.36
     Exceptional
    0.36
    தார
    0.34
     دیگر
    0.34
     よ
    0.33
     నేపథ
    0.33
     实
    0.33
     preparatory
    0.33
     கட
    0.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.