© 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. 142733
    Prev
    Next
    INDEX
    Explanations

    list of words or phrases following certain tokens

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

    areas impacted

    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
     נוס
    0.54
     krzy
    0.48
    וא
    0.45
    あ
    0.43
    }^{-
    0.42
    òi
    0.42
    와의
    0.42
    ǒ
    0.42
     rejuvenation
    0.41
     vē
    0.41
    POSITIVE LOGITS
     ২০২২
    0.51
     Responses
    0.49
     Tokens
    0.49
     Integer
    0.46
     تحصل
    0.46
     macOS
    0.45
     Sparse
    0.44
     Patreon
    0.44
     Any
    0.43
     Classes
    0.42
    Activations Density 0.001%

    No Known Activations