© 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. 106446
    Prev
    Next
    INDEX
    Explanations

    numbers, quantifiers, or sequence starters

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

    AI terms, developers, users

    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
    綑
    0.50
     לו
    0.48
    bestand
    0.44
    在他的
    0.43
    <unused635>
    0.43
     vrt
    0.43
    ವೀ
    0.42
    剛
    0.42
     ถาม
    0.42
     كات
    0.42
    POSITIVE LOGITS
    ed
    0.51
    copyWith
    0.49
     usuários
    0.49
    canc
    0.49
     sang
    0.47
     exemplaires
    0.47
     ڈویل
    0.46
    ellations
    0.46
    or
    0.46
     superiores
    0.46
    Activations Density 0.000%

    No Known Activations