© 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. 242486
    Prev
    Next
    INDEX
    Explanations

    sudden shift, also known, money is

    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
    ール
    0.52
    Ď
    0.50
    covariant
    0.49
     MyRegisterClass
    0.48
    Ḍ
    0.47
     nisid
    0.47
     ஒன்றிய
    0.46
    ನೆ
    0.46
     hauptsächlich
    0.46
    ち
    0.45
    POSITIVE LOGITS
     restructure
    0.49
     y
    0.45
     qu
    0.45
    羡
    0.44
    clus
    0.44
     sublimation
    0.44
     pry
    0.44
     infect
    0.43
     rook
    0.43
     grabar
    0.43
    Activations Density 0.000%

    No Known Activations