© 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. 40-GEMMASCOPE-2-RES-65K
    7. 824
    Prev
    Next
    INDEX
    Explanations

    wikipedia urls

    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_40_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
    ชื่อ
    0.39
     végétation
    0.37
    庵
    0.37
    ุณ
    0.36
     otvor
    0.36
    酤
    0.36
     isomorphisms
    0.36
    탄소년단
    0.35
    ørt
    0.35
    Animations
    0.35
    POSITIVE LOGITS
     ck
    0.39
     TV
    0.35
    set
    0.34
     ২৫
    0.33
    ckpt
    0.33
    âng
    0.33
     CDs
    0.33
     CD
    0.32
    CMake
    0.32
     =\
    0.32
    Activations Density 0.057%

    No Known Activations