© 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. 42226
    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
     we
    -2.56
     márm
    -1.99
    𖥦
    -1.91
    ᷇
    -1.88
    ῞
    -1.84
    玏
    -1.83
    醅
    -1.83
     delikat
    -1.82
    …！
    -1.80
    ਲ਼
    -1.78
    POSITIVE LOGITS
    </td>
    2.11
    </h5>
    1.95
    ant
    1.91
    us
    1.89
    In
    1.87
    </em>
    1.76
    b
    1.75
    ",
    1.74
    ta
    1.70
     is
    1.69
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.