© 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. 31-GEMMASCOPE-2-RES-262K
    4. 3597
    Prev
    Next
    INDEX
    Explanations

    line segments, areas, or matrices

    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_31_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
    餐饮
    0.33
    фессиона
    0.31
    আমার
    0.30
    撳
    0.30
    ayutt
    0.29
    细腻
    0.29
    经纪
    0.29
    ⵖ
    0.29
    基础设施
    0.29
    渔
    0.29
    POSITIVE LOGITS
     almost
    0.36
     maximum
    0.36
     two
    0.35
     half
    0.34
     trivially
    0.34
     a
    0.34
     monotonically
    0.34
     max
    0.34
     monotonic
    0.34
     maximal
    0.33
    Activations Density 0.453%

    No Known Activations