© 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. 168621
    Prev
    Next
    INDEX
    Explanations

    by followed by attribution or clause

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

    base isolation

    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
     شوي
    0.49
     مع
    0.48
     тан
    0.47
    ！
    0.47
     Š
    0.46
     मर्द
    0.45
     تو
    0.45
    ０
    0.43
    яти
    0.43
     //
    0.42
    POSITIVE LOGITS
     rassembl
    0.49
    꼰
    0.48
    車の
    0.47
    vrage
    0.46
    ங்களாக
    0.45
    czne
    0.45
    icole
    0.45
    om
    0.45
    ණ්ඩ
    0.44
     uczniów
    0.44
    Activations Density 0.002%

    No Known Activations