© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32923
    Prev
    Next
    INDEX
    Explanations

    nice as a positive descriptor

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

    nice adjective modifying positive attributes

    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
    the
    0.77
    ม
    0.76
    0
    0.68
     that
    0.66
    nın
    0.63
     CLASSES
    0.61
     Workshops
    0.60
     Internation
    0.60
     your
    0.59
     Waves
    0.59
    POSITIVE LOGITS
     nice
    0.84
    Nice
    0.82
    in
    0.78
    p
    0.72
    id
    0.71
    р
    0.70
    v
    0.70
    綺麗な
    0.68
    nice
    0.67
    漂亮
    0.66
    Activations Density 0.031%

    No Known Activations