© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 143898
    Prev
    Next
    INDEX
    Explanations

    must ask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ುಕ
    0.52
    ExpireTime
    0.50
    arrêt
    0.49
    햇
    0.48
    혐
    0.47
    Вер
    0.46
    ਿਰ
    0.46
    찍
    0.45
    Се
    0.45
    enregist
    0.45
    POSITIVE LOGITS
     dif
    0.48
     Project
    0.48
     Key
    0.47
     Page
    0.47
     ch
    0.47
     Panel
    0.43
     Important
    0.43
     Nottingham
    0.43
     to
    0.42
    ,
    0.42
    Activations Density 0.003%

    No Known Activations