© 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. 25362
    Prev
    Next
    INDEX
    Explanations

    change or worse context

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

    AI discourse

    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
     injustices
    0.45
     supplement
    0.43
     injustice
    0.43
     supplements
    0.43
     stems
    0.42
    ти
    0.42
    -
    0.40
    hend
    0.40
    objs
    0.40
    -}$
    0.40
    POSITIVE LOGITS
     Иң
    0.55
     モダン
    0.54
     صہیونی
    0.52
     используются
    0.52
     ប៉ុ
    0.52
     μέχρι
    0.51
    を使用
    0.50
     ましょう
    0.50
     轻
    0.50
     কক্ষে
    0.49
    Activations Density 0.000%

    No Known Activations