© 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. 61246
    Prev
    Next
    INDEX
    Explanations

    explaining actions, concepts, code, and priorities

    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
     manipulation
    0.57
     mac
    0.53
     Core
    0.52
     BAS
    0.52
     laundering
    0.52
     TIFF
    0.51
     '
    0.51
     acid
    0.51
     at
    0.50
     contains
    0.50
    POSITIVE LOGITS
     شرطونه
    0.50
    fie
    0.47
    ௫
    0.47
    ϲ
    0.46
    ALOG
    0.46
    Meine
    0.45
     પરિવાર
    0.45
    ದಯ
    0.45
    ९
    0.45
     общество
    0.44
    Activations Density 0.007%

    No Known Activations