© 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. 44517
    Prev
    Next
    INDEX
    Explanations

    fetching data with requests

    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
    '
    0.49
     संर
    0.47
    õ
    0.46
    ่
    0.43
    upp
    0.43
    는
    0.42
    රු
    0.42
    ↵
    0.42
    šti
    0.41
    وانه
    0.41
    POSITIVE LOGITS
    滢
    0.52
     gesund
    0.44
     biomed
    0.43
    狲
    0.43
    ből
    0.43
    Thay
    0.43
    AnimationFrame
    0.43
     टेक्नोलॉजी
    0.43
    Disabled
    0.43
    ழுப்பு
    0.42
    Activations Density 0.001%

    No Known Activations