Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13862
    Prev
    Next
    INDEX
    Explanations

    code declaration and input

    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
    if
    0.52
    ните
    0.49
    Ли
    0.49
    ธ์
    0.47
    threads
    0.45
    마
    0.45
    index
    0.44
    น
    0.44
    Х
    0.44
    성
    0.44
    POSITIVE LOGITS
     Profits
    0.48
     Holes
    0.43
     Removes
    0.41
     TWO
    0.40
     يَ
    0.39
     merci
    0.39
     Surplus
    0.39
     gde
    0.39
     Troy
    0.38
     μαύ
    0.38
    Activations Density 0.013%

    No Known Activations