© 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. 247723
    Prev
    Next
    INDEX
    Explanations

    wine tasting

    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
    umā
    0.52
    edel
    0.48
     बेहत
    0.48
    inflammation
    0.47
    க
    0.47
    ोत्तर
    0.46
     Caedwalla
    0.46
    疾病
    0.46
    lemish
    0.46
    થી
    0.46
    POSITIVE LOGITS
    %
    0.50
     kor
    0.46
     komm
    0.45
     「
    0.44
     win
    0.44
     comm
    0.43
    Yup
    0.43
     are
    0.42
     নিউজ
    0.42
     was
    0.42
    Activations Density 0.001%

    No Known Activations