© 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. 52453
    Prev
    Next
    INDEX
    Explanations

    copy writer

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

    closed eyes, lost in thought

    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
     냉
    0.55
     stein
    0.50
     hok
    0.50
     bos
    0.48
     shar
    0.47
     elekt
    0.47
     tik
    0.47
     zwycię
    0.47
     groe
    0.47
     psycho
    0.47
    POSITIVE LOGITS
    2
    0.55
    ES
    0.54
    1
    0.51
    es
    0.50
    भारत
    0.48
    IF
    0.48
    index
    0.47
    IS
    0.47
    (
    0.46
    CHICAGO
    0.46
    Activations Density 0.000%

    No Known Activations