© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13757
    Prev
    Next
    INDEX
    Explanations

    copyright year

    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_16k_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
     ७
    0.41
     tika
    0.40
     ती
    0.39
     bottles
    0.38
     simplification
    0.37
     ich
    0.37
    ega
    0.36
    रिक
    0.36
     "="
    0.36
    rát
    0.36
    POSITIVE LOGITS
    去年
    0.48
     ২০১০
    0.46
    昨年
    0.45
     বছ
    0.43
     ২০২১
    0.40
     ۲۰۱
    0.40
    近年来
    0.39
    Ꭾ
    0.38
    PhysicalDevice
    0.38
    邢
    0.38
    Activations Density 0.026%

    No Known Activations