© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57393
    Prev
    Next
    INDEX
    Explanations

    the [noun or descriptor]

    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
     are
    -1.54
     spearheaded
    -1.47
     exceedingly
    -1.43
    c
    -1.42
     exceptionally
    -1.41
     of
    -1.39
     joyous
    -1.39
     viviendo
    -1.37
    太多的
    -1.37
     jugando
    -1.36
    POSITIVE LOGITS
     what
    2.11
     if
    1.77
    喜歡
    1.73
    cepat
    1.68
    šnje
    1.64
     specified
    1.62
     विश्वसनीयता
    1.61
    ミ
    1.61
    følge
    1.60
    nių
    1.59
    Activations Density 0.349%

    No Known Activations