© 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. 10-GEMMASCOPE-RES-131K
    7. 66899
    Prev
    Next
    INDEX
    Explanations

    main page, menu, toolbar, graph

    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
    灃
    -1.83
    ⩴
    -1.80
    厹
    -1.77
    ୪
    -1.70
    )
    -1.68
    沨
    -1.63
    甃
    -1.59
    奇怪
    -1.59
    
    -1.59
    during
    -1.56
    POSITIVE LOGITS
    そこから
    1.91
     даже
    1.87
     prado
    1.84
    c
    1.84
    a
    1.80
    r
    1.74
    鲣
    1.71
    お子
    1.65
     Even
    1.64
    f
    1.60
    Activations Density 0.029%

    No Known Activations