© 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. 105997
    Prev
    Next
    INDEX
    Explanations

    expresses desire or intent

    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
     italia
    -1.98
    vereignty
    -1.98
     luxem
    -1.90
     gonz
    -1.86
    vereign
    -1.84
    蚡
    -1.83
     ZX
    -1.79
    datable
    -1.79
    moiselle
    -1.77
    itarianism
    -1.77
    POSITIVE LOGITS
     you
    2.52
     (‘
    2.00
     ‘
    1.93
     our
    1.90
     this
    1.88
    {
    1.85
     many
    1.79
     It
    1.78
     «
    1.67
     ‘‘
    1.66
    Activations Density 0.001%

    No Known Activations