© 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. 119955
    Prev
    Next
    INDEX
    Explanations

    founding members and partners

    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
    他说
    -1.75
     admitir
    -1.52
     secador
    -1.52
     staunch
    -1.50
    瑧
    -1.49
    hythm
    -1.46
    سبة
    -1.42
     vivía
    -1.42
    butuhkan
    -1.41
     debió
    -1.41
    POSITIVE LOGITS
    \
    1.78
    le
    1.60
    j
    1.56
    to
    1.52
    眚
    1.49
    橚
    1.48
    d
    1.47
    po
    1.46
    as
    1.45
    ⏑
    1.45
    Activations Density 0.011%

    No Known Activations