© 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. 31671
    Prev
    Next
    INDEX
    Explanations

    several times or multiple instances

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

    multiple occurrences

    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
    bank
    0.43
    Bank
    0.41
    उनकी
    0.40
    gen
    0.39
    新的
    0.39
    mind
    0.39
    lobal
    0.38
    %!
    0.38
    murder
    0.38
    norod
    0.38
    POSITIVE LOGITS
    几次
    1.07
     twice
    1.00
    多次
    0.97
     several
    0.95
    何度
    0.95
     plusieurs
    0.93
     varias
    0.92
     कई
    0.91
    两次
    0.91
     عدة
    0.90
    Activations Density 0.088%

    No Known Activations