© 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. 31-GEMMASCOPE-2-RES-65K
    7. 11090
    Prev
    Next
    INDEX
    Explanations

    list item formatting

    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
    辭
    0.40
    arquía
    0.40
    ตอน
    0.39
    國
    0.38
     считать
    0.38
    藝術
    0.37
    芸術
    0.36
    涫
    0.36
    체를
    0.36
    ningar
    0.36
    POSITIVE LOGITS
     ngunit
    0.49
     but
    0.47
     ولكن
    0.43
     possui
    0.43
     😊
    0.43
    ↵↵
    0.43
     pero
    0.42
     futile
    0.42
     permeable
    0.42
     bandage
    0.42
    Activations Density 0.004%

    No Known Activations