© 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. 78007
    Prev
    Next
    INDEX
    Explanations

    meeting your needs and goals

    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
    包
    -0.96
    貢
    -0.93
     or
    -0.91
    karz
    -0.91
    edo
    -0.89
    ﺭ
    -0.89
     accomplishment
    -0.89
    gá
    -0.88
    activities
    -0.87
    orsal
    -0.85
    POSITIVE LOGITS
     wildest
    1.05
     variadas
    1.00
     varied
    0.91
     diverse
    0.90
     دیکھیے
    0.89
     increasingly
    0.88
     varying
    0.84
     highest
    0.84
     variados
    0.80
     various
    0.79
    Activations Density 0.033%

    No Known Activations