© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103064
    Prev
    Next
    INDEX
    Explanations

    possibility and frequency

    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
    ではでは
    -1.73
    0
    -1.70
    Slik
    -1.66
    儛
    -1.64
     then
    -1.62
    顚
    -1.57
    Karakter
    -1.55
    を増
    -1.52
    Fakta
    -1.52
    2
    -1.48
    POSITIVE LOGITS
     is
    1.75
     to
    1.61
    ˃
    1.54
    ϱ
    1.54
    MAXN
    1.53
     тысячи
    1.52
    穎
    1.49
     What
    1.45
    NameValuePair
    1.44
    \'{
    1.43
    Activations Density 0.163%

    No Known Activations