© 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. 198870
    Prev
    Next
    INDEX
    Explanations

    free WiFi

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

    email, task, issue, furniture

    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
    Negative Logits
    ing
    0.56
     endeavoured
    0.49
    торое
    0.47
    を有する
    0.46
     fastener
    0.45
    issances
    0.44
    ي
    0.44
    sensor
    0.43
    ricted
    0.42
    remeno
    0.42
    POSITIVE LOGITS
     pribadi
    0.49
     estil
    0.47
    ὥ
    0.46
    arrière
    0.46
     uitz
    0.45
     Bina
    0.44
    钚
    0.44
     bernama
    0.43
     iTunes
    0.42
     "\"
    0.42
    Activations Density 0.002%

    No Known Activations