© 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-262K
    7. 32003
    Prev
    Next
    INDEX
    Explanations

    table or icon definitions

    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_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
     washers
    0.39
    ロゴ
    0.39
     rilas
    0.38
    擠
    0.38
     métal
    0.38
    箍
    0.37
     آور
    0.37
     logotipo
    0.37
     octobre
    0.36
     emblems
    0.36
    POSITIVE LOGITS
    drawer
    0.45
    守
    0.39
    LAYOUT
    0.39
    账户
    0.39
    Eth
    0.38
    addView
    0.38
     sparse
    0.38
    Drawer
    0.38
     பருவ
    0.38
    SRS
    0.38
    Activations Density 0.000%

    No Known Activations