© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 200
    Prev
    Next
    INDEX
    Explanations

    character types and styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    ంప
    0.70
    ிற்கும்
    0.70
     زیادہ
    0.69
    κά
    0.67
     للصف
    0.67
     nêu
    0.67
    든지
    0.67
    ం
    0.66
    ร้าง
    0.65
     ایک
    0.64
    POSITIVE LOGITS
     orator
    0.86
     warrior
    0.86
     apert
    0.86
     gather
    0.84
    尊
    0.83
     pride
    0.81
     Gust
    0.81
     fires
    0.81
     extraordinaire
    0.80
    ophile
    0.79
    Activations Density 0.830%

    No Known Activations