© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1381
    Prev
    Next
    INDEX
    Explanations

    phrases ending in punctuation or questions

    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
     perkembangan
    0.80
    ilization
    0.80
     berjumpa
    0.78
    
    0.77
     mencipt
    0.76
    性和
    0.76
    롭게
    0.71
    aurus
    0.71
    leştir
    0.71
    ແລະ
    0.71
    POSITIVE LOGITS
     ท
    0.98
     ا
    0.97
     แต่
    0.97
     ل
    0.93
     ب
    0.92
     لا
    0.91
     ย
    0.89
     ن
    0.89
     إ
    0.89
     แม
    0.88
    Activations Density 0.036%

    No Known Activations