© 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. 13507
    Prev
    Next
    INDEX
    Explanations

    fork

    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
    in
    1.57
    f
    1.30
    t
    1.11
    ۰
    1.02
    inna
    0.99
    。
    0.93
    inje
    0.92
    game
    0.91
    g
    0.91
    el
    0.89
    POSITIVE LOGITS
    ’
    1.54
    -
    1.21
    '
    1.13
    "
    1.13
     destac
    1.09
     fork
    1.03
    quela
    0.99
    ²
    0.96
    ни
    0.94
    ب
    0.94
    Activations Density 0.002%

    No Known Activations