© 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-65K
    7. 56607
    Prev
    Next
    INDEX
    Explanations

    nature of things

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Graduate
    0.47
     conducteur
    0.44
    дым
    0.44
    এখন
    0.42
    า
    0.42
     දැන්
    0.42
     PREVENTION
    0.41
    )¶
    0.41
     громадян
    0.41
     вла
    0.40
    POSITIVE LOGITS
    /
    0.45
     bamboo
    0.44
     suman
    0.44
     obscured
    0.43
    ceso
    0.43
    /(
    0.42
     claw
    0.42
     snappy
    0.41
    ionicons
    0.41
     fing
    0.40
    Activations Density 0.007%

    No Known Activations