© 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. 209182
    Prev
    Next
    INDEX
    Explanations

    protect your

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

    foreign words and definitions

    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
    AL
    0.52
    ^{-}$
    0.47
     PEP
    0.47
    DT
    0.46
    SL
    0.46
    PK
    0.45
    LI
    0.45
    clerc
    0.45
    PS
    0.45
    PEP
    0.44
    POSITIVE LOGITS
    ⾃
    0.50
     تغيير
    0.49
    ರುವ
    0.49
     efectuar
    0.49
     entrer
    0.48
    変更
    0.47
     powied
    0.47
    етки
    0.47
     REGIUNI
    0.46
     définir
    0.46
    Activations Density 0.000%

    No Known Activations