© 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. 92385
    Prev
    Next
    INDEX
    Explanations

    Sporting events

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

    cute, geek, case, companies

    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
    ภา
    0.50
    ну
    0.46
    ২২
    0.46
    激
    0.46
    май
    0.45
    тур
    0.41
    。（
    0.41
    λό
    0.41
    娥
    0.41
    ρι
    0.41
    POSITIVE LOGITS
     insanın
    0.47
    estab
    0.45
     apareció
    0.45
     emperors
    0.44
     apparaître
    0.44
     sympa
    0.43
     الانسان
    0.43
     کش
    0.43
     Vivekan
    0.42
     apparaît
    0.42
    Activations Density 0.001%

    No Known Activations