© 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. 8749
    Prev
    Next
    INDEX
    Explanations

    exceptionalism

    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
    S
    1.09
    E
    1.09
    ۹
    1.09
    H
    1.08
    ä
    1.08
    C
    1.07
    P
    1.06
    V
    1.05
     to
    1.02
    K
    1.02
    POSITIVE LOGITS
    ก
    0.80
     cans
    0.79
     contests
    0.77
     Bakers
    0.77
     bookshelves
    0.76
     cumprimento
    0.76
     Ephesians
    0.76
     Buses
    0.74
     Administrative
    0.74
    ত্বের
    0.73
    Activations Density 0.000%

    No Known Activations