© 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. 9451
    Prev
    Next
    INDEX
    Explanations

    act of composing

    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
    ia
    1.57
    し
    1.57
     on
    1.50
    د
    1.29
    .
    1.24
    จะ
    1.23
    ır
    1.19
    ется
    1.18
    ться
    1.14
    д
    1.13
    POSITIVE LOGITS
    দের
    1.27
     Composition
    1.14
    ون
    1.08
     composers
    1.06
    kita
    1.06
    Composition
    1.05
     Фурга
    1.05
     kompos
    1.05
    ٣
    1.05
    。
    1.04
    Activations Density 0.013%

    No Known Activations