© 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. 89633
    Prev
    Next
    INDEX
    Explanations

    whole fish

    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
     lascia
    0.49
     paed
    0.47
     kriminal
    0.47
     considerazione
    0.46
     ČR
    0.46
     கரு
    0.46
    给人
    0.45
     eSIM
    0.45
    ⚒
    0.45
     सड़क
    0.44
    POSITIVE LOGITS
    ت
    0.42
    блю
    0.42
    ದ
    0.42
     populations
    0.42
     hourglass
    0.41
    eligible
    0.40
     وصل
    0.39
    SCALE
    0.39
    licher
    0.39
     Catalina
    0.39
    Activations Density 0.005%

    No Known Activations