© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 171995
    Prev
    Next
    INDEX
    Explanations

    starting Tuesday

    np_acts-logits-general · gemini-2.5-flash-lite

    personalità, personnalité, personalidade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     تسه
    0.53
    袒
    0.49
     Permanente
    0.49
     ن
    0.45
     Error
    0.45
     H
    0.45
     G
    0.45
     Assigned
    0.45
     انت
    0.44
    (
    0.44
    POSITIVE LOGITS
     personnalité
    0.49
     personalità
    0.49
     ব্যক্তিত্ব
    0.49
     wrists
    0.48
     personalidade
    0.48
     bravely
    0.47
     dziecka
    0.46
     cinemat
    0.46
     сообщи
    0.46
     osobow
    0.46
    Activations Density 0.001%

    No Known Activations