© 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. 94549
    Prev
    Next
    INDEX
    Explanations

    business and organizations

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

    documentation and classification

    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
    Not in Any Lists

    No Comments

    Negative Logits
     vari
    0.50
     saveData
    0.47
     테
    0.46
     Lagrangian
    0.46
     autom
    0.46
     kom
    0.46
     IL
    0.46
     thicken
    0.45
     kir
    0.44
    Lake
    0.44
    POSITIVE LOGITS
     wronged
    0.48
    िएट
    0.45
    asına
    0.44
    hesus
    0.44
    вшись
    0.43
    ﺿ
    0.42
    utente
    0.42
    asional
    0.42
    संहार
    0.42
    ЕВ
    0.42
    Activations Density 0.000%

    No Known Activations