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-65K
    4. 27877
    Prev
    Next
    INDEX
    Explanations

    asking questions and explaining

    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_65k_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
    நர்
    0.45
    if
    0.43
    λλ
    0.42
    하거나
    0.39
    ᓗ
    0.39
    Rescue
    0.38
    或
    0.38
    ashed
    0.38
    నో
    0.38
     or
    0.38
    POSITIVE LOGITS
     opět
    0.55
     אשר
    0.51
     입니다
    0.50
     yaitu
    0.47
    쫀득
    0.45
     पुन्हा
    0.45
     वस्त्र
    0.44
     ਦਵਾਈ
    0.44
     בח
    0.43
    ﷻ
    0.43
    Activations Density 0.020%

    No Known Activations