© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21548
    Prev
    Next
    INDEX
    Explanations

    Calls or refers to sports/business

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dissol
    0.38
    spirited
    0.38
    ombe
    0.37
    den
    0.36
    asers
    0.35
     beasts
    0.35
    நீர்
    0.35
    akoti
    0.35
    쾨
    0.35
    ప్రత్యర్థి
    0.34
    POSITIVE LOGITS
    Calls
    0.48
     Calls
    0.48
     preferential
    0.47
     Pillar
    0.47
     Cast
    0.45
    calls
    0.45
     flo
    0.44
     charging
    0.43
     calls
    0.42
    Cast
    0.42
    Activations Density 0.001%

    No Known Activations