© 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. 62874
    Prev
    Next
    INDEX
    Explanations

    parameters and params

    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
    rijving
    -0.93
     curled
    -0.91
     okru
    -0.90
    stuhl
    -0.83
     karet
    -0.82
    (')
    -0.81
     romain
    -0.81
    Engl
    -0.81
     ané
    -0.79
     portu
    -0.78
    POSITIVE LOGITS
    或许
    0.77
    cinq
    0.74
    fdb
    0.73
    似乎
    0.71
     Mutable
    0.69
    啷
    0.68
    问
    0.68
    tický
    0.68
    奇怪
    0.67
     toxin
    0.67
    Activations Density 0.011%

    No Known Activations