© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 138926
    Prev
    Next
    INDEX
    Explanations

    dilates pupils or depends on

    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
    ア
    0.54
    ני
    0.52
    电商
    0.45
    タ
    0.44
    Pack
    0.44
    条
    0.43
    ك
    0.43
    iki
    0.43
    参考
    0.42
    雷
    0.42
    POSITIVE LOGITS
     greenish
    0.50
     diminution
    0.47
     insoluble
    0.47
     trifling
    0.47
     gewähr
    0.46
     yellowish
    0.46
     Haupt
    0.46
     resid
    0.45
     unwarrant
    0.45
     Zentr
    0.45
    Activations Density 0.005%

    No Known Activations