© 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. 4076
    Prev
    Next
    INDEX
    Explanations

    more than twenty percent

    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
     Су
    0.51
    주
    0.48
    들이
    0.47
    РА
    0.46
    וי
    0.45
    의
    0.44
     Một
    0.43
    들도
    0.43
    ක
    0.43
    Ссылки
    0.43
    POSITIVE LOGITS
    t
    0.61
    ol
    0.39
    é
    0.39
    ן
    0.38
    ain
    0.38
    tans
    0.37
    olon
    0.36
    mē
    0.36
     όχι
    0.36
    ázej
    0.36
    Activations Density 0.405%

    No Known Activations