© 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. 50645
    Prev
    Next
    INDEX
    Explanations

    have no

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

    formal, expository phrasing that states processes or causal/logical relations (e.g., “X uses Y to do Z,” “If… then…,” “functions to…”) often found in definitions, instructions, and multiple‑choice/legal statements.

    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
    пись
    0.44
    кий
    0.44
    ті
    0.43
    romyalgia
    0.41
    imizi
    0.41
    힣
    0.41
    كُمْ
    0.41
    casa
    0.40
    années
    0.40
     техника
    0.40
    POSITIVE LOGITS
     stars
    0.45
     attempts
    0.42
     breadth
    0.42
     begins
    0.40
     crux
    0.40
     dispensers
    0.39
    ኸ
    0.39
     widgets
    0.38
     begint
    0.38
     seeds
    0.38
    Activations Density 0.115%

    No Known Activations