© 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. 169614
    Prev
    Next
    INDEX
    Explanations

    money, text features, or code structures

    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
    يرات
    0.41
    hts
    0.41
    люми
    0.41
     помі
    0.39
    定向
    0.39
     ພວກເຮົາ
    0.38
     Lipp
    0.38
    鏢
    0.38
    closures
    0.38
     quartic
    0.38
    POSITIVE LOGITS
     dripping
    0.44
     drip
    0.44
     hatching
    0.41
     inner
    0.39
     Info
    0.39
     drips
    0.38
     kiles
    0.38
     creeps
    0.37
     enjoyed
    0.36
     ctrl
    0.36
    Activations Density 0.003%

    No Known Activations