© 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. 11507
    Prev
    Next
    INDEX
    Explanations

    George Washington

    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
    وان
    0.88
     of
    0.85
    ř
    0.83
    氛
    0.82
     einen
    0.79
    ors
    0.77
    كل
    0.77
    3
    0.77
    वे
    0.76
    )}\
    0.75
    POSITIVE LOGITS
    is
    1.77
    n
    1.45
    <0x80>
    1.19
    to
    1.19
    ли
    1.18
    at
    1.17
    an
    1.13
    '
    1.12
    for
    1.10
    ’
    1.10
    Activations Density 0.001%

    No Known Activations