© 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. 192234
    Prev
    Next
    INDEX
    Explanations

    find duplicate files

    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
    贰百
    0.40
     фактически
    0.40
    醎
    0.40
     Localization
    0.40
     Manifesto
    0.40
    ncies
    0.40
     뛰
    0.39
    ᑦ
    0.39
     Пол
    0.38
     எப்படி
    0.38
    POSITIVE LOGITS
     hybrid
    0.49
     communal
    0.42
     híbr
    0.41
     jossa
    0.40
    VID
    0.39
    iran
    0.38
    াকৃতিক
    0.38
    hybrid
    0.38
     malware
    0.37
    alf
    0.37
    Activations Density 0.002%

    No Known Activations