© 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. 107879
    Prev
    Next
    INDEX
    Explanations

    why are, established in, yet tasted

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

    summaries, explanations, or descriptions

    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
    )~
    0.47
     JFrame
    0.46
     वृन्दावन
    0.45
    InputCommand
    0.43
     Schematic
    0.43
     OFFICE
    0.42
     Fuck
    0.42
     DELIVERY
    0.42
    )}_{
    0.42
     Incoming
    0.42
    POSITIVE LOGITS
     moyennes
    0.49
    πάρχ
    0.48
     တယ်
    0.48
     travaillons
    0.47
    графі
    0.46
     thérapeut
    0.46
     souver
    0.45
    半島
    0.44
     nourrir
    0.44
     différences
    0.44
    Activations Density 0.001%

    No Known Activations