© 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. 53354
    Prev
    Next
    INDEX
    Explanations

    specific words following common tokens

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

    about what is suggested

    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
    p
    0.57
    cion
    0.50
    b
    0.48
    cadherin
    0.46
    厲
    0.45
    bef
    0.44
    cte
    0.44
    cbc
    0.44
    ^{-}
    0.44
    cb
    0.43
    POSITIVE LOGITS
     എന്ന്
    0.51
     პირადი
    0.48
     terletak
    0.48
     ist
    0.47
    的功能
    0.46
     Hydra
    0.46
     adhipp
    0.46
     Рассмотрим
    0.46
     briefly
    0.45
     considere
    0.45
    Activations Density 0.000%

    No Known Activations