© 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. 65512
    Prev
    Next
    INDEX
    Explanations

    all followed by classifications

    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
     and
    -2.16
    \
    -1.82
    &#
    -1.52
    ↵↵↵
    -1.51
    this
    -1.50
     '
    -1.47
     &#
    -1.47
    unjungi
    -1.46
    申し上げます
    -1.42
    0
    -1.42
    POSITIVE LOGITS
     revisor
    1.69
    OCOLATE
    1.65
    partimento
    1.63
     ritard
    1.63
     vitrine
    1.62
     persua
    1.61
     paradis
    1.59
     espal
    1.57
    ellido
    1.57
    quelize
    1.57
    Activations Density 0.004%

    No Known Activations