© 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. 3036
    Prev
    Next
    INDEX
    Explanations

    . following sentence

    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
    Negative Logits
     Piers
    0.44
    త్
    0.43
     স্বয়ং
    0.42
    INDER
    0.40
    หรือไม่
    0.39
    Coins
    0.38
    替换
    0.38
    謎
    0.38
     Poles
    0.38
     Coins
    0.38
    POSITIVE LOGITS
    izing
    0.45
    enca
    0.43
    č
    0.43
    ப்ப
    0.42
    ensem
    0.41
    indent
    0.41
    au
    0.41
    éri
    0.41
    ativ
    0.40
    ilen
    0.40
    Activations Density 0.012%

    No Known Activations