© 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. 141997
    Prev
    Next
    INDEX
    Explanations

    authors present research

    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
    л
    0.98
    ıll
    0.86
    az
    0.85
     SRAM
    0.82
     author
    0.80
     THE
    0.80
     Author
    0.79
    Author
    0.79
    an
    0.78
    ?
    0.77
    POSITIVE LOGITS
    نا
    1.27
    ين
    1.18
    م
    1.12
    ம்
    1.04
    ج
    1.02
    1
    0.99
    س
    0.95
    ی
    0.93
    هم
    0.92
    ности
    0.91
    Activations Density 0.002%

    No Known Activations