© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2023
    Prev
    Next
    INDEX
    Explanations

    completes the request, open weights, like patching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ---------------
    0.74
     số
    0.71
    <0xAF>
    0.71
    September
    0.70
     الس
    0.69
    Số
    0.68
     สี
    0.68
    S
    0.67
     Số
    0.66
    送料
    0.66
    POSITIVE LOGITS
     കാണ
    0.42
    哪怕
    0.42
     vaguely
    0.42
     کاربران
    0.41
     сек
    0.40
     کە
    0.40
     curvatures
    0.40
    <unused47>
    0.39
    极为
    0.39
    |</
    0.38
    Activations Density 0.516%

    No Known Activations