© 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. 11870
    Prev
    Next
    INDEX
    Explanations

    double or double-check

    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
    单一
    0.49
    single
    0.48
    単
    0.48
    단을
    0.46
    マルチ
    0.43
    单
    0.43
     делают
    0.41
    SINGLE
    0.41
     yks
    0.40
     単
    0.40
    POSITIVE LOGITS
     Double
    1.01
     double
    0.98
    Double
    0.90
    double
    0.88
     डबल
    0.85
    ダブル
    0.75
     DOUBLE
    0.74
     ダブル
    0.72
    parseDouble
    0.72
     doble
    0.66
    Activations Density 0.007%

    No Known Activations