© 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. 31910
    Prev
    Next
    INDEX
    Explanations

    actor, he, they

    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
     Karne
    0.54
    伲
    0.50
     Jü
    0.49
    詳しくは
    0.49
    섦
    0.49
    锕
    0.48
    ZIONE
    0.48
    Ｂ
    0.48
    綪
    0.48
     فشاں
    0.47
    POSITIVE LOGITS
     on
    0.64
    ka
    0.59
    as
    0.57
    im
    0.57
    os
    0.57
    7
    0.54
    ate
    0.51
    ales
    0.50
    jang
    0.50
    ign
    0.50
    Activations Density 0.000%

    No Known Activations