© 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. 16-GEMMASCOPE-2-RES-262K
    7. 31731
    Prev
    Next
    INDEX
    Explanations

    cargo new

    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_16_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
    ，
    0.71
    ال
    0.67
    ；
    0.62
    ü
    0.60
     måde
    0.58
    ?
    0.58
     en
    0.57
     me
    0.57
    ী
    0.55
     ele
    0.53
    POSITIVE LOGITS
     چھوٹ
    0.60
    新潟
    0.59
     комитета
    0.57
     தேசிய
    0.57
     ক্লিক
    0.57
     ಅಗತ್ಯ
    0.57
     третье
    0.56
     комите
    0.55
     ಸಂಬಂಧ
    0.55
     фран
    0.55
    Activations Density 0.001%

    No Known Activations