© 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. 58353
    Prev
    Next
    INDEX
    Explanations

    financial and technical data analysis

    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
     ミュ
    -0.69
    سال
    -0.69
    Back
    -0.68
    <blockquote>
    -0.68
    ыгана
    -0.68
     Gallon
    -0.67
    期刊论文
    -0.67
     增
    -0.67
     ikea
    -0.66
     sequin
    -0.66
    POSITIVE LOGITS
    classmethod
    0.87
    UNICODE
    0.86
    maxY
    0.85
    Radians
    0.84
    nande
    0.83
    edt
    0.82
     noir
    0.77
    plotlib
    0.76
     nad
    0.75
     cellules
    0.75
    Activations Density 0.006%

    No Known Activations