© 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. 40-GEMMASCOPE-2-RES-262K
    7. 215541
    Prev
    Next
    INDEX
    Explanations

    visual descriptions and code setup

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    芴
    0.42
    atively
    0.40
     phổi
    0.40
    ̚
    0.40
    цый
    0.39
     Dumb
    0.39
    க்கூ
    0.39
    𒀭
    0.39
    朼
    0.39
     पुत्री
    0.38
    POSITIVE LOGITS
     reflections
    0.43
     Reflections
    0.42
     passing
    0.40
     Genres
    0.39
     områ
    0.38
    grö
    0.38
     pokaż
    0.37
     scal
    0.37
     seid
    0.37
     moving
    0.37
    Activations Density 0.000%

    No Known Activations