© 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. 9020
    Prev
    Next
    INDEX
    Explanations

    types of content

    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
    Not in Any Lists

    No Comments

    Negative Logits
     shenanigans
    0.27
     dichotomy
    0.23
     caveats
    0.22
     covariates
    0.22
    Ი
    0.21
     covariate
    0.21
     convolutions
    0.21
    활동
    0.21
     memnun
    0.20
    仠
    0.20
    POSITIVE LOGITS
    <unused2141>
    0.20
    selecting
    0.19
    assara
    0.18
    igion
    0.18
     เช่น
    0.17
    ames
    0.17
    iume
    0.17
    agge
    0.17
     forests
    0.17
    iumi
    0.17
    Activations Density 0.112%

    No Known Activations