© 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. 3075
    Prev
    Next
    INDEX
    Explanations

    whole word matching

    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
     peritoneal
    0.47
     gz
    0.46
     swimwear
    0.46
     nacional
    0.44
     sme
    0.44
     spt
    0.44
     स्वयं
    0.43
    西方
    0.42
    '];
    0.42
     sarc
    0.42
    POSITIVE LOGITS
    MSP
    0.46
    getItems
    0.46
     生命
    0.44
    iao
    0.43
    ESS
    0.42
    ủy
    0.42
    beatable
    0.42
     விவர
    0.41
     అన్ని
    0.41
     öffnen
    0.41
    Activations Density 0.002%

    No Known Activations