© 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. 72920
    Prev
    Next
    INDEX
    Explanations

    tool review

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

    influencing policy or relationships

    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
    这样做
    0.52
    리카
    0.51
     свое
    0.51
    事務
    0.49
    卒
    0.48
     rightfully
    0.47
     своё
    0.47
    ુદ્ધ
    0.46
    AGA
    0.45
     hides
    0.44
    POSITIVE LOGITS
     값이
    0.50
     ገ
    0.50
     سلاٹ
    0.47
     lä
    0.47
     Mä
    0.46
    ötet
    0.46
     Lä
    0.46
     Św
    0.46
     소비자
    0.46
    pluck
    0.46
    Activations Density 0.000%

    No Known Activations