© 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. 58439
    Prev
    Next
    INDEX
    Explanations

    explaining namely

    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
     berarti
    -0.88
     Особенно
    -0.84
     böyle
    -0.84
     også
    -0.82
     también
    -0.82
    sillon
    -0.80
    ullable
    -0.80
    también
    -0.79
    思います
    -0.78
    𝙠
    -0.78
    POSITIVE LOGITS
     namely
    7.84
    namely
    6.00
     nämlich
    5.88
     Namely
    5.69
     totiž
    4.91
     namelijk
    4.88
     nemlig
    4.63
     näm
    3.88
     viz
    3.64
     yaitu
    3.56
    Activations Density 0.219%

    No Known Activations