© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7482
    Prev
    Next
    INDEX
    Explanations

    ASIL level relevance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Adresse
    0.52
    碐
    0.51
     преподава
    0.50
    𒀕
    0.46
     చక్ర
    0.45
    侔
    0.45
     [&](
    0.45
     impediments
    0.45
    鿆
    0.45
    }^{*}(\
    0.45
    POSITIVE LOGITS
    ,
    0.54
    WA
    0.50
    .
    0.50
    #
    0.49
    ERA
    0.48
    Insect
    0.46
     sua
    0.46
     pitcher
    0.45
    ;
    0.45
     or
    0.44
    Activations Density 0.017%

    No Known Activations