© 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. 14206
    Prev
    Next
    INDEX
    Explanations

    Founding Fathers and Shah

    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
    سی
    1.13
    IN
    1.05
    ்த
    1.05
    ם
    1.04
    OS
    1.00
    یم
    1.00
    いた
    1.00
    acja
    0.98
    ولی
    0.97
    ندی
    0.97
    POSITIVE LOGITS
    of
    1.64
    ↵↵
    1.45
    al
    1.34
     of
    1.09
    含ま
    1.05
     불구하고
    1.02
    ة
    0.94
     على
    0.93
    使用
    0.92
    他的
    0.91
    Activations Density 0.010%

    No Known Activations