© 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. 185653
    Prev
    Next
    INDEX
    Explanations

    mounting ring

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

    Jetson, simmer, juvenile, disclaimer, RAC1, collision, Observe

    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
    Negative Logits
    ’
    0.45
    діть
    0.45
     Solicitors
    0.42
    pheus
    0.42
    away
    0.41
     Ичиго
    0.41
     ಪೊಲೀಸ
    0.41
    စည်း
    0.39
    liament
    0.39
    rainment
    0.39
    POSITIVE LOGITS
     величи
    0.52
     furo
    0.46
     настроение
    0.46
    孱
    0.45
    痊
    0.44
    NetAmount
    0.43
    哒
    0.43
    িষ্ট
    0.43
     զ
    0.43
    边缘
    0.42
    Activations Density 0.001%

    No Known Activations