© 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. 362
    Prev
    Next
    INDEX
    Explanations

    provided at the end

    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
    测量
    0.50
     壁
    0.47
    牛仔
    0.46
    澳洲
    0.45
    迪士
    0.43
     grill
    0.43
     ranchers
    0.43
     కలిసి
    0.42
    Укра
    0.42
    测
    0.42
    POSITIVE LOGITS
    otto
    0.48
    directory
    0.47
    ot
    0.47
    r
    0.46
    lette
    0.45
    red
    0.45
    lt
    0.43
    b
    0.43
    at
    0.42
    ww
    0.42
    Activations Density 0.028%

    No Known Activations