© 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. 197445
    Prev
    Next
    INDEX
    Explanations

    medical, technical, or descriptive terms

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

    title, tuple, too thin, animals, lower highs, today, zip archive

    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
    Shares
    0.50
    PPE
    0.47
    妷
    0.46
    ári
    0.45
     ماند
    0.45
     লাগিল
    0.45
     संशोधन
    0.44
    l
    0.44
    FT
    0.43
    Share
    0.43
    POSITIVE LOGITS
    캄
    0.50
    astanza
    0.48
    予想
    0.45
    ಬಹುದು
    0.44
    ňuje
    0.44
     verwendet
    0.43
    隼
    0.43
     زندگی
    0.42
     Vereinigten
    0.42
     cento
    0.42
    Activations Density 0.000%

    No Known Activations