© 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. 47839
    Prev
    Next
    INDEX
    Explanations

    extracting files, parallel strings, metadata changes, small files

    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
    floral
    0.54
    Floral
    0.48
    től
    0.46
     spécialiste
    0.46
    術
    0.45
    kaj
    0.45
     Forestry
    0.44
     convexes
    0.44
    枒
    0.44
    👪
    0.44
    POSITIVE LOGITS
     blinked
    0.44
     leaked
    0.43
     이루
    0.41
     stubbornly
    0.41
     necessary
    0.40
     sorely
    0.39
     hammered
    0.39
     troublesome
    0.38
     vaguely
    0.36
     faintly
    0.36
    Activations Density 0.007%

    No Known Activations