© 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. 133975
    Prev
    Next
    INDEX
    Explanations

    destructuring a sequence

    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
     pendant
    0.38
    絕對
    0.38
     soud
    0.37
    葦
    0.37
    決済
    0.36
     Абра
    0.36
     élő
    0.35
    绝对
    0.35
    Definitely
    0.34
    мок
    0.34
    POSITIVE LOGITS
     unpack
    0.93
     unpacking
    0.91
     Dest
    0.90
    unpack
    0.89
     dest
    0.88
    Dest
    0.87
     destruct
    0.86
    dest
    0.85
     unpacked
    0.81
     ({
    0.73
    Activations Density 0.047%

    No Known Activations