© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 229414
    Prev
    Next
    INDEX
    Explanations

    RAM, TV, Companion, cases

    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
    пі
    0.54
    вих
    0.54
    堇
    0.51
    媤
    0.49
     сю
    0.49
    вена
    0.49
    宻
    0.49
    伲
    0.48
    τία
    0.48
    绫
    0.48
    POSITIVE LOGITS
    ↵↵
    0.56
     they
    0.54
    ne
    0.51
     t
    0.49
    ing
    0.49
    view
    0.49
    iter
    0.48
     negligently
    0.48
    ................
    0.47
     algae
    0.47
    Activations Density 0.001%

    No Known Activations