© 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. 17493
    Prev
    Next
    INDEX
    Explanations

    shoe or horseshoe

    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
    r
    1.43
    is
    1.27
    to
    1.23
    t
    1.23
    지
    1.23
    dır
    1.14
    sp
    1.12
    ž
    1.10
    나
    1.10
    lü
    1.09
    POSITIVE LOGITS
    ING
    0.93
    ↵
    0.87
     불구하고
    0.86
     mailed
    0.84
     Олимпий
    0.82
    ASH
    0.80
    I
    0.80
     đựng
    0.80
     Амери
    0.80
    <0xB6>
    0.79
    Activations Density 0.004%

    No Known Activations