© 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. 84030
    Prev
    Next
    INDEX
    Explanations

    multi-script words

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

    naming follows pattern

    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
    O
    0.54
     MV
    0.52
    ن
    0.52
    MV
    0.51
    T
    0.48
     O
    0.47
     Mine
    0.46
     CLAIM
    0.45
    Mine
    0.45
     Vineyard
    0.44
    POSITIVE LOGITS
    sunny
    0.61
    perror
    0.55
     सनी
    0.54
    óso
    0.54
    ंचित
    0.51
     햇
    0.51
     филосо
    0.50
    mater
    0.50
    adım
    0.50
     باسک
    0.50
    Activations Density 0.001%

    No Known Activations