© 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. 101426
    Prev
    Next
    INDEX
    Explanations

    body parts or actions

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

    safe, inside, country, interests, PC

    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
    Щ
    0.51
    。
    0.50
    V
    0.45
    Liên
    0.45
     quarrel
    0.44
    definite
    0.44
    이었
    0.43
    occur
    0.43
    両
    0.43
    Ошибка
    0.43
    POSITIVE LOGITS
     stadiums
    0.52
     場
    0.49
     انگ
    0.47
     Atmosphäre
    0.47
     ligands
    0.47
    🤠
    0.47
     isotopes
    0.46
     genotyping
    0.46
    richtung
    0.45
     สนาม
    0.45
    Activations Density 0.000%

    No Known Activations