© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3853
    Prev
    Next
    INDEX
    Explanations

    by followed by action

    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
    м
    0.30
    म
    0.29
    م
    0.28
    ية
    0.25
    ل
    0.24
    ר
    0.24
    ↵
    0.23
    ல்
    0.22
    el
    0.21
    ro
    0.21
    POSITIVE LOGITS
     dint
    0.27
     virtue
    0.26
     работой
    0.22
    서는
    0.21
    瞠
    0.21
    zantine
    0.21
     дизайн
    0.20
     inserting
    0.19
    products
    0.19
     всё
    0.19
    Activations Density 0.271%

    No Known Activations