© 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-16K
    7. 13752
    Prev
    Next
    INDEX
    Explanations

    style characteristics and applications

    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_16k_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
    2
    0.90
    ين
    0.83
    dır
    0.81
    lar
    0.73
    din
    0.70
    ले
    0.69
    ी
    0.68
    ler
    0.67
     buddy
    0.66
    る
    0.65
    POSITIVE LOGITS
    ０
    0.80
    ۰
    0.80
     스타일
    0.78
     정책
    0.77
    정책
    0.77
    STYLE
    0.77
    policy
    0.76
     стиль
    0.73
     STYLE
    0.72
    風格
    0.72
    Activations Density 0.114%

    No Known Activations