© 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. 5699
    Prev
    Next
    INDEX
    Explanations

    Succession, Happ, Creates

    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
    nicheskij
    0.57
    iwers
    0.56
    ၀
    0.54
    partial
    0.52
    horizontal
    0.52
    ಿಕೊಂಡ
    0.50
    wtf
    0.48
    ０
    0.47
    branchNode
    0.47
    porcion
    0.47
    POSITIVE LOGITS
     Rosen
    0.41
    ాయ
    0.39
     Hanson
    0.38
     웹
    0.38
     appell
    0.38
     examinations
    0.38
    astas
    0.38
     Best
    0.37
     OFF
    0.37
     Photos
    0.37
    Activations Density 0.010%

    No Known Activations