© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90846
    Prev
    Next
    INDEX
    Explanations

    Mura statistical, Pdf PCell, AtIndexPath iOS

    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
    ?”
    -3.16
    -”
    -3.13
     felpa
    -3.09
    镦
    -2.97
     sirena
    -2.95
    鋮
    -2.81
     hadas
    -2.77
     エントランス
    -2.73
    —”
    -2.70
     goma
    -2.69
    POSITIVE LOGITS
    "
    4.53
    {
    3.86
     "
    3.30
    ...
    2.55
     We
    2.50
    +\
    2.50
    ,"
    2.44
    et
    2.42
    ↵
    2.42
    ',
    2.41
    Activations Density 0.006%

    No Known Activations