© 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-262K
    7. 30269
    Prev
    Next
    INDEX
    Explanations

    code snippets and comments

    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_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
     deduce
    0.51
     diğer
    0.49
    傩
    0.48
     perspiciatis
    0.48
     réfléch
    0.46
     differentiable
    0.46
    z
    0.46
     hacemos
    0.45
    niji
    0.45
     qualify
    0.44
    POSITIVE LOGITS
    <0x0D>
    0.50
    ндай
    0.48
    十足
    0.45
    ม
    0.45
    Solved
    0.45
    唒
    0.45
     آمد
    0.43
    \")
    0.43
     হয়েছে
    0.43
    쉼
    0.43
    Activations Density 0.016%

    No Known Activations