© 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. 205586
    Prev
    Next
    INDEX
    Explanations

    address, research, or scheduling variables

    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
     discíp
    0.50
     прошу
    0.47
    遄
    0.46
    髗
    0.46
    FirstResponder
    0.45
    轳
    0.44
    ECUT
    0.44
    неоп
    0.44
     Comando
    0.44
    洧
    0.44
    POSITIVE LOGITS
    %
    0.49
    err
    0.48
    riek
    0.45
    atsby
    0.42
     injected
    0.41
    vars
    0.40
    ake
    0.40
    ats
    0.40
    isel
    0.40
    ield
    0.39
    Activations Density 0.008%

    No Known Activations