© 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. 26230
    Prev
    Next
    INDEX
    Explanations

    bol followed by word endings

    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
    Roma
    0.40
    كذا
    0.38
    离开了
    0.37
    odoxy
    0.36
     обратить
    0.36
    ?}
    0.36
    apabb
    0.36
     गूगल
    0.35
    ❈
    0.35
    !}
    0.35
    POSITIVE LOGITS
     bol
    0.76
    Bol
    0.75
     бол
    0.70
     Bol
    0.70
     boli
    0.61
     BOL
    0.60
    BOL
    0.59
    bol
    0.57
     Bolton
    0.55
     Bolts
    0.52
    Activations Density 0.004%

    No Known Activations