© 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-262K
    7. 108494
    Prev
    Next
    INDEX
    Explanations

    Wright brothers

    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_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
    dplyr
    0.45
    𒈠
    0.42
    kenalkan
    0.42
    溶解
    0.42
    偶像
    0.41
    ចែកចាយ
    0.41
    रियो
    0.40
    僭
    0.40
     Jerzy
    0.40
    typedef
    0.39
    POSITIVE LOGITS
    0.52
     runs
    0.42
     strategic
    0.42
     roots
    0.42
     frozen
    0.42
     menjal
    0.41
     blizzard
    0.41
     breaks
    0.41
     dense
    0.40
     στε
    0.40
    Activations Density 0.017%

    No Known Activations