© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32766
    Prev
    Next
    INDEX
    Explanations

    ranking and positions

    np_acts-logits-general · gemini-2.5-flash-lite

    ranking items by order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     분류
    0.66
     classify
    0.64
    nico
    0.63
     classifying
    0.61
     定义
    0.61
    h
    0.61
    ي
    0.61
    Grouping
    0.58
    b
    0.57
    厂
    0.57
    POSITIVE LOGITS
     Rank
    0.73
     rank
    0.72
     RANK
    0.68
     रैंक
    0.67
    Rank
    0.62
     ranks
    0.60
     ranked
    0.60
    RANK
    0.59
    排行
    0.58
     Rankings
    0.55
    Activations Density 0.014%

    No Known Activations