© 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. 110520
    Prev
    Next
    INDEX
    Explanations

    trying to present

    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
    动机
    0.44
     Gian
    0.43
     Wetland
    0.43
    ;
    0.43
     জগ
    0.42
     Circuit
    0.41
     Torrent
    0.41
     POM
    0.41
     Aragon
    0.41
     rector
    0.41
    POSITIVE LOGITS
    hitva
    0.49
    muslim
    0.45
     самих
    0.42
     istilah
    0.42
    `:
    0.42
    𝙠
    0.41
     dajj
    0.41
    baixo
    0.40
     savages
    0.40
     stockp
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.