© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 223298
    Prev
    Next
    INDEX
    Explanations

    symbols and code snippets

    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_40_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
     to
    0.84
     a
    0.77
     Перейти
    0.75
     ہے۔
    0.72
     🌱
    0.65
     preuve
    0.63
     เช่น
    0.59
     spooky
    0.59
     |
    0.59
     blatant
    0.59
    POSITIVE LOGITS
    an
    1.05
    သောအ
    1.04
    in
    0.98
    for
    0.95
    that
    0.94
    and
    0.89
    u
    0.88
    o
    0.82
    the
    0.81
    form
    0.80
    Activations Density 0.178%

    No Known Activations