© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128200
    Prev
    Next
    INDEX
    Explanations

    homeschooled children, Life of Fred, photography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ',
    -1.95
    鈦
    -1.91
     impetus
    -1.72
    '
    -1.71
     '',
    -1.70
    媪
    -1.70
     encontrar
    -1.69
    饪
    -1.65
     länge
    -1.64
     indicar
    -1.63
    POSITIVE LOGITS
    with
    2.33
    for
    2.02
    based
    1.85
    but
    1.79
    櫺
    1.76
    not
    1.63
     fährt
    1.60
    his
    1.57
    鱘
    1.57
     felpa
    1.56
    Activations Density 0.007%

    No Known Activations