© 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. 42772
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and abbreviations

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

    generate uniform designs

    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
    níků
    0.46
    utm
    0.44
     parametros
    0.44
     tackling
    0.42
    類
    0.42
    スペック
    0.42
    su
    0.41
    ný
    0.41
    ada
    0.41
     ณ
    0.41
    POSITIVE LOGITS
     үшін
    0.43
    chine
    0.43
    rían
    0.42
    暾
    0.41
    滪
    0.41
    巴西
    0.41
    োপুরি
    0.41
     combed
    0.40
     интен
    0.40
    化妆
    0.40
    Activations Density 0.082%

    No Known Activations