© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9983
    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
    </strong>
    -2.70
    s
    -2.31
     and
    -1.73
    imanapun
    -1.73
     certitude
    -1.60
    </h1>
    -1.59
    蜮
    -1.56
     by
    -1.55
    ければ
    -1.54
    termilk
    -1.53
    POSITIVE LOGITS
    </td>
    2.23
    nitus
    1.84
     recibo
    1.76
    </
    1.72
     weist
    1.70
     \\
    1.66
     versteht
    1.66
    摠
    1.63
     conseguiu
    1.63
    ")]
    
    1.61
    Activations Density 0.000%

    No Known Activations