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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48759
    Prev
    Next
    INDEX
    Explanations

    view() function calls

    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_40_width_65k_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
    レベル
    0.44
    මණ
    0.41
    বলী
    0.38
    layouts
    0.37
    กาย
    0.37
    өрү
    0.37
    梓
    0.37
     হইতেছে
    0.37
    mois
    0.37
    ಿಸಲಾಗಿದೆ
    0.36
    POSITIVE LOGITS
     rich
    0.39
     керек
    0.39
    iyaki
    0.38
     ப்
    0.38
     უ
    0.38
    HH
    0.38
    hhhh
    0.37
    hhh
    0.37
    rich
    0.37
    hh
    0.37
    Activations Density 0.001%

    No Known Activations