© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12803
    Prev
    Next
    INDEX
    Explanations

    disable

    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
    嵛
    -1.95
     prized
    -1.92
     veritable
    -1.81
     ?
    -1.80
    曖昧さ
    -1.77
     hapless
    -1.76
    ﺀ
    -1.70
     appelé
    -1.70
    蓠
    -1.69
     aptly
    -1.66
    POSITIVE LOGITS
    前
    1.91
    with
    1.79
    </
    1.77
    、
    1.73
     سبتمبر
    1.73
     czemu
    1.70
    )$
    1.61
    )。
    1.60
     Desember
    1.59
    m
    1.59
    Activations Density 0.021%

    No Known Activations