© 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. 123920
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    到
    -0.92
    monger
    -0.91
    但是
    -0.90
    isome
    -0.89
    ēd
    -0.88
    aday
    -0.86
    timg
    -0.83
    botten
    -0.83
    ardin
    -0.83
    ñata
    -0.83
    POSITIVE LOGITS
     vrijdag
    1.06
    Какой
    1.04
     zondag
    0.96
     inovasi
    0.96
    右边
    0.94
    ając
    0.93
     from
    0.90
    lín
    0.89
     miraculous
    0.89
    amkeit
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.