© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92621
    Prev
    Next
    INDEX
    Explanations

    voicing opinions

    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_34/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
     Divi
    -0.77
    否认
    -0.75
    мови
    -0.74
    (>
    -0.73
    спери
    -0.73
     منه
    -0.72
    っちり
    -0.72
     (;
    -0.71
     saludo
    -0.71
    eners
    -0.71
    POSITIVE LOGITS
     voice
    3.69
     voicing
    3.63
     voiced
    3.59
     express
    3.56
     expressing
    3.50
     expressed
    3.17
     expresses
    3.09
    Express
    2.88
    express
    2.88
     Express
    2.80
    Activations Density 0.067%

    No Known Activations