© 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. 16-GEMMASCOPE-2-RES-262K
    4. 13655
    Prev
    Next
    INDEX
    Explanations

    Gutenberg, marketplace, programming, books

    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
     be
    0.51
    )$
    0.51
     lesion
    0.50
    وست
    0.49
    rophy
    0.48
     crowns
    0.46
     cicat
    0.46
     problém
    0.46
     euros
    0.45
     salesman
    0.45
    POSITIVE LOGITS
    <h2>
    0.50
    หนังสือ
    0.49
     А
    0.47
    нин
    0.46
     книга
    0.45
     Андрей
    0.44
     книге
    0.43
     Що
    0.43
     технология
    0.42
     навіть
    0.42
    Activations Density 0.010%

    No Known Activations