© 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. 1827
    Prev
    Next
    INDEX
    Explanations

    words starting with K, Ver, Ge

    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
    BlockFit
    0.34
     TabLayout
    0.33
    🛹
    0.32
    𒁁
    0.32
    ຼ
    0.32
    ↼
    0.31
    ֮
    0.31
    <unused1083>
    0.31
    лый
    0.31
    GoAbroad
    0.31
    POSITIVE LOGITS
     e
    0.35
     S
    0.33
     D
    0.32
    io
    0.32
    if
    0.31
    N
    0.31
     M
    0.31
    ä
    0.31
    č
    0.30
     N
    0.30
    Activations Density 0.005%

    No Known Activations