Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 1787
    Prev
    Next
    INDEX
    Explanations

    available resources and spots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    מו
    0.61
    Gram
    0.59
     composed
    0.57
     ידי
    0.57
    ย์
    0.56
     utilizando
    0.55
    composed
    0.54
    P
    0.52
    Bep
    0.52
    respective
    0.52
    POSITIVE LOGITS
    สำหรับ
    0.87
    充足
    0.86
    សម្រាប់
    0.84
     کافی
    0.84
     확보
    0.81
     adequate
    0.80
     disponibles
    0.79
     disponible
    0.78
     для
    0.78
     AVAILABLE
    0.77
    Activations Density 0.712%

    No Known Activations