© 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. 117869
    Prev
    Next
    INDEX
    Explanations

    purpose for, product of, keep track, companies like

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

    form submission or validation

    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
     އ
    0.47
    修复
    0.42
    鹏
    0.42
    仳
    0.42
     பா
    0.41
     помощью
    0.41
     მ
    0.41
     ფ
    0.41
    Repair
    0.41
    И
    0.41
    POSITIVE LOGITS
     combustibles
    0.52
     litres
    0.50
    urine
    0.49
    वाही
    0.49
    idemargin
    0.48
    ंदर
    0.47
    ocy
    0.47
    ้ว
    0.45
    agland
    0.45
     didn
    0.44
    Activations Density 0.000%

    No Known Activations