© 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-65K
    7. 5044
    Prev
    Next
    INDEX
    Explanations

    include logging, May be, simply gathering

    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_65k_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
     devast
    0.29
    ಟೆ
    0.26
    <unused294>
    0.26
    <unused398>
    0.26
    зор
    0.25
    <unused416>
    0.25
    तोष
    0.25
    <unused254>
    0.25
     conducta
    0.25
    <unused573>
    0.25
    POSITIVE LOGITS
     with
    0.38
    with
    0.36
     WITH
    0.36
    เมื่อ
    0.32
     which
    0.30
     according
    0.30
     containing
    0.29
    を使用
    0.29
    如果你
    0.28
    内で
    0.28
    Activations Density 0.377%

    No Known Activations