© 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. 152982
    Prev
    Next
    INDEX
    Explanations

    gift items

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

    heart rate

    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
    νη
    0.49
     opérés
    0.48
     consulter
    0.46
    чках
    0.46
    ด
    0.45
    бы
    0.45
     управля
    0.45
    フ
    0.44
    وبه
    0.44
    ｱ
    0.44
    POSITIVE LOGITS
     habido
    0.52
     Profil
    0.49
     dinner
    0.48
     loading
    0.47
    க்கான
    0.47
     pertain
    0.47
    ları
    0.46
     Incluso
    0.46
     RAD
    0.45
    raphy
    0.45
    Activations Density 0.001%

    No Known Activations