© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66616
    Prev
    Next
    INDEX
    Explanations

    Victoria and Victorian places

    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
    lış
    -1.40
    metre
    -1.37
     Brazilian
    -1.36
     Brazil
    -1.34
    endos
    -1.28
     Spain
    -1.27
     hatte
    -1.27
     Oklahoma
    -1.27
    ="
    -1.27
    <td>
    -1.27
    POSITIVE LOGITS
     

    1.33
    ึกษา
    1.16
     renegade
    1.16
    pertina
    1.16
     Renegade
    1.14
     necessários
    1.13
     verstär
    1.13
     facades
    1.08
     burlesque
    1.07
     vertraut
    1.07
    Activations Density 0.050%

    No Known Activations