© 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. 104023
    Prev
    Next
    INDEX
    Explanations

    assassin Ferdinand; dashed lines/stroke

    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
    瑆
    0.57
    खर
    0.56
    𝙙
    0.54
    球队
    0.53
    อย่างไร
    0.52
     הם
    0.50
     ಹೇಗೆ
    0.50
    Angleterre
    0.50
    昰
    0.50
     ছিলেন
    0.49
    POSITIVE LOGITS
    j
    0.91
    es
    0.69
    al
    0.67
    at
    0.66
    ви
    0.66
    g
    0.66
    wes
    0.66
    mano
    0.62
    مان
    0.61
    w
    0.61
    Activations Density 0.003%

    No Known Activations