© 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. 20664
    Prev
    Next
    INDEX
    Explanations

    C++ typedef

    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
    ing
    1.05
    um
    1.02
    sm
    1.02
    rs
    0.96
    im
    0.94
    sc
    0.92
    g
    0.89
    ar
    0.89
    ur
    0.83
    ou
    0.83
    POSITIVE LOGITS
    ت
    1.07
     мужчин
    0.99
    کل
    0.98
    '
    0.93
    coon
    0.87
     август
    0.86
    ことで
    0.86
    网友
    0.86
    ને
    0.84
    ותו
    0.82
    Activations Density 0.001%

    No Known Activations