© 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. 142136
    Prev
    Next
    INDEX
    Explanations

    speech to text

    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
    ی
    0.95
    ти
    0.93
    ни
    0.88
    ের
    0.86
    ओं
    0.86
    тів
    0.86
    s
    0.84
    ті
    0.83
    тэй
    0.80
     quitter
    0.79
    POSITIVE LOGITS
    ，
    0.66
    ที่คุณ
    0.64
    โดย
    0.60
    n
    0.59
    ANCY
    0.59
     ως
    0.57
     insieme
    0.57
     biasa
    0.57
    Insect
    0.57
    婴
    0.57
    Activations Density 0.001%

    No Known Activations