© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3428
    Prev
    Next
    INDEX
    Explanations

    Fischer

    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_17_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
     สำหรับ
    0.99
    สำหรับ
    0.91
    所以在
    0.88
     Untuk
    0.86
     想
    0.82
     Pentru
    0.78
     Чтобы
    0.78
     بالنسبه
    0.77
     Think
    0.76
     gotta
    0.75
    POSITIVE LOGITS
    راک
    0.71
    ?:
    0.68
     aspetti
    0.66
     aunque
    0.66
    雖
    0.66
     despite
    0.64
     much
    0.63
     atti
    0.63
    kien
    0.63
     attributes
    0.63
    Activations Density 0.118%

    No Known Activations