© 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. 16-GEMMASCOPE-2-RES-262K
    7. 46385
    Prev
    Next
    INDEX
    Explanations

    philosophy and config paths

    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_16_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
    ి
    0.83
    ي
    0.79
    i
    0.77
    تي
    0.76
    iénd
    0.67
    י
    0.67
    ி
    0.66
    。“
    0.65
    I
    0.64
    ი
    0.63
    POSITIVE LOGITS
     aliquot
    0.59
     unsubscribe
    0.58
    ʟ
    0.57
    ும்
    0.55
    ра
    0.55
     luật
    0.54
     inhalation
    0.54
    ्रल
    0.54
    싶
    0.53
    凌
    0.53
    Activations Density 0.009%

    No Known Activations