© 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. 194559
    Prev
    Next
    INDEX
    Explanations

    storylines

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

    grammatical constructions and specific words

    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
    詐
    0.49
    ائز
    0.48
    stv
    0.48
    確立
    0.46
     aute
    0.46
     strategie
    0.46
     بونس
    0.45
    æ
    0.45
     hiểu
    0.45
     okres
    0.45
    POSITIVE LOGITS
    3
    0.52
    ON
    0.50
    4
    0.49
    preferably
    0.49
    lipped
    0.47
     BOOKS
    0.47
     preferably
    0.46
     INFIN
    0.46
     UV
    0.45
    s
    0.45
    Activations Density 0.000%

    No Known Activations