© 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. 226956
    Prev
    Next
    INDEX
    Explanations

    virus types

    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
    ിയാണ്
    0.48
    銠
    0.46
     finalizing
    0.45
    ਗੀ
    0.44
    organic
    0.44
    აცია
    0.44
    ようやく
    0.42
    โล
    0.42
    roweak
    0.42
    題
    0.42
    POSITIVE LOGITS
     hilfre
    0.52
     коллекции
    0.50
    大切な
    0.50
     мастер
    0.48
    pathTo
    0.48
     Pru
    0.48
     аксессу
    0.47
     naturaleza
    0.46
     های
    0.46
     сверх
    0.46
    Activations Density 0.005%

    No Known Activations