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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 2337
    Prev
    Next
    INDEX
    Explanations

    various categories and types

    np_acts-logits-general · gemini-2.5-flash-lite

    document-structure and formatting cues—like section headers, numbered/bulleted list markers, and emphasis indicators—signaling organized list or outline formatting.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     ylim
    0.32
     kanamycin
    0.31
     portata
    0.31
     ق
    0.30
    った
    0.29
     cline
    0.29
     operands
    0.29
     rafters
    0.28
     этого
    0.28
     সেখানে
    0.28
    POSITIVE LOGITS
     विविध
    0.34
     각종
    0.34
     다양한
    0.33
    さまざまな
    0.33
     LGBTQ
    0.31
     различные
    0.31
    អេឡិចត្រូនិច
    0.31
     besides
    0.31
    Besides
    0.31
     specialised
    0.31
    Activations Density 0.943%

    No Known Activations