© 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. 96756
    Prev
    Next
    INDEX
    Explanations

    save more, allows users, help refine

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

    explaining why

    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
     aches
    0.44
     koos
    0.44
    TextViewStyle
    0.42
    т
    0.42
    ান্তর
    0.40
     continuo
    0.40
    ſſ
    0.39
     recitation
    0.39
     rearing
    0.38
     incessant
    0.38
    POSITIVE LOGITS
     हस्तक्षेप
    0.53
     చివరి
    0.52
     Créd
    0.49
     معروف
    0.49
     రెండు
    0.49
    譏
    0.49
     सुद्धा
    0.48
     المعروف
    0.47
     גדול
    0.46
     επίσης
    0.46
    Activations Density 0.000%

    No Known Activations