© 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. 41419
    Prev
    Next
    INDEX
    Explanations

    Marshall followed by Plan, Jefferson, Rosenberg, Islands

    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
    t
    2.02
    y
    1.45
    at
    1.39
    c
    1.38
    p
    1.37
    z
    1.34
    u
    1.32
    da
    1.30
    et
    1.28
    s
    1.19
    POSITIVE LOGITS
    ä
    1.11
     Marshall
    1.10
    ’
    1.06
     marshall
    1.00
     marsh
    0.94
    는
    0.92
    จะ
    0.92
    ۔
    0.89
    ่
    0.88
    ने
    0.87
    Activations Density 0.001%

    No Known Activations