© 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-262K
    7. 10954
    Prev
    Next
    INDEX
    Explanations

    javascript console statements

    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_262k_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
    ,
    0.61
     in
    0.54
     pickled
    0.45
     converting
    0.44
     unob
    0.43
     cui
    0.43
    йма
    0.42
     viss
    0.42
    ేవ
    0.42
    antibodies
    0.42
    POSITIVE LOGITS
    -}
    0.52
    0
    0.48
    價
    0.48
    ０
    0.48
    ur
    0.46
     그는
    0.46
    Agregar
    0.45
    फ्रेंस
    0.45
    console
    0.45
    Console
    0.45
    Activations Density 0.021%

    No Known Activations