© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21658
    Prev
    Next
    INDEX
    Explanations

    free, clear, reuse, luck

    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
     доб
    0.47
    शुभ
    0.46
    Khi
    0.46
    ש
    0.44
    autumn
    0.44
    ં
    0.44
     చివరి
    0.43
     ಆರಂಭ
    0.43
     тако
    0.41
    वृद्धि
    0.41
    POSITIVE LOGITS
     wireless
    0.53
     television
    0.52
     radio
    0.52
     device
    0.51
     data
    0.50
     widescreen
    0.48
     a
    0.48
     stereo
    0.48
     handheld
    0.48
     iPod
    0.47
    Activations Density 0.003%

    No Known Activations