© 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. 66061
    Prev
    Next
    INDEX
    Explanations

    for purposes of

    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
    会被
    -2.05
     všech
    -1.93
     BOTH
    -1.73
     altamente
    -1.66
     reconocido
    -1.66
     destacado
    -1.63
     zweif
    -1.61
     dangers
    -1.59
     mostrando
    -1.59
     variadas
    -1.59
    POSITIVE LOGITS
    шают
    2.05
    This
    2.00
    n
    1.94
    .”
    1.89
    the
    1.81
    k
    1.79
    sequently
    1.76
    h
    1.75
    ”
    1.74
    اگر
    1.70
    Activations Density 0.011%

    No Known Activations