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. 53-GEMMASCOPE-2-RES-262K
    4. 82587
    Prev
    Next
    INDEX
    Explanations

    describing styles and categories

    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_53_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
     ―
    0.43
     Mathematical
    0.42
     marina
    0.41
     biota
    0.40
     ны
    0.39
     millennium
    0.38
     баста
    0.38
     вода
    0.38
     gând
    0.38
     styr
    0.38
    POSITIVE LOGITS
    antemente
    0.40
    辏
    0.39
    পূ
    0.39
     toast
    0.38
    žit
    0.38
    সি
    0.37
     إص
    0.37
    창
    0.37
    琦
    0.36
    tmpobj
    0.36
    Activations Density 0.002%

    No Known Activations