© 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. 945
    Prev
    Next
    INDEX
    Explanations

    quotation marks and slashes

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

    books and authors

    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
    Strafpunkte
    0.50
    Therates
    0.47
    FreeFlag
    0.45
    鱻
    0.45
    沇
    0.44
    निश्ड
    0.44
    듐
    0.44
    颞
    0.44
    蠵
    0.43
    颏
    0.43
    POSITIVE LOGITS
    ,
    0.52
    pl
    0.52
     R
    0.51
    pre
    0.50
    -
    0.50
     T
    0.49
    M
    0.48
    R
    0.48
    V
    0.48
    h
    0.48
    Activations Density 0.398%

    No Known Activations