© 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. 12924
    Prev
    Next
    INDEX
    Explanations

    boats and boating activities

    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
    陕西
    0.47
    鉱
    0.47
    隗
    0.47
    Afghanistan
    0.45
    கோவை
    0.44
     profinite
    0.43
    jTextField
    0.42
     बीएड
    0.42
    赳
    0.42
    大地
    0.41
    POSITIVE LOGITS
     boat
    2.31
     boating
    2.14
     boats
    2.13
     Boat
    1.98
     Boats
    1.95
    Boat
    1.93
    boat
    1.90
    boats
    1.80
     BOAT
    1.80
     sailboats
    1.71
    Activations Density 0.022%

    No Known Activations