© 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. 76093
    Prev
    Next
    INDEX
    Explanations

    noun followed by adjective or verb

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

    child develops, possessing damaging, modular robotics, safety first

    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
    非常
    0.47
    烈的
    0.47
    ció
    0.45
     období
    0.43
     engen
    0.42
    也非常
    0.42
    ív
    0.41
    ጩ
    0.41
    色的
    0.40
    兴
    0.40
    POSITIVE LOGITS
     Scholarships
    0.49
     জনে
    0.48
    ে
    0.46
     Membuat
    0.46
    るので
    0.45
     அடிப்பட
    0.43
     умолчанию
    0.43
     tokamaks
    0.42
     Foundations
    0.42
     Making
    0.41
    Activations Density 0.002%

    No Known Activations