© 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-262K
    7. 220658
    Prev
    Next
    INDEX
    Explanations

    list items and definitions

    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_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
     leads
    0.41
    ’
    0.41
     makes
    0.40
     earns
    0.39
     solves
    0.39
    '
    0.39
     earned
    0.38
    Whatever
    0.38
    ...\
    0.38
     finishes
    0.38
    POSITIVE LOGITS
    樍
    0.44
    ėtų
    0.42
    这才
    0.41
    グループ
    0.40
     الثلاث
    0.39
    imètres
    0.39
     ಬೇ
    0.39
     ट्रॉप
    0.39
     دې
    0.38
     progrès
    0.38
    Activations Density 0.001%

    No Known Activations