Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 211185
    Prev
    Next
    INDEX
    Explanations

    evaluation and lists

    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
    抂
    0.45
    募
    0.40
    条款
    0.39
    沌
    0.39
    絊
    0.39
     स्पेशल
    0.39
    لمات
    0.39
     የመ
    0.39
    autiful
    0.38
    pecial
    0.38
    POSITIVE LOGITS
     Compiler
    0.44
     accelerator
    0.42
     \
    0.41
     hack
    0.40
     Interaction
    0.40
     র‌
    0.40
     stacking
    0.38
    称
    0.38
     compiler
    0.38
     accelerators
    0.38
    Activations Density 0.001%

    No Known Activations