© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 6168
    Prev
    Next
    INDEX
    Explanations

    multiplication tables

    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
    денциа
    0.46
    भंगा
    0.46
     coagulation
    0.43
    फना
    0.43
    করিয়া
    0.43
     తగ్గ
    0.41
    jaan
    0.41
    😙
    0.41
    ിച്ചി
    0.41
    ğine
    0.41
    POSITIVE LOGITS
     multiplication
    0.66
     Multiplication
    0.59
     multiplications
    0.55
     Math
    0.54
     math
    0.53
     multiplying
    0.53
     Quiz
    0.52
     matemáticas
    0.51
     quiz
    0.46
     maths
    0.46
    Activations Density 0.002%

    No Known Activations