© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20664
    Prev
    Next
    INDEX
    Explanations

    the X and the Y

    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
     they
    -2.06
     "
    -1.93
    皤
    -1.91
    able
    -1.49
     “
    -1.48
     Drž
    -1.45
    就要
    -1.44
     They
    -1.41
    enswert
    -1.41
     slechts
    -1.40
    POSITIVE LOGITS
     whatnot
    2.31
    zembro
    1.70
    rafas
    1.60
    leggio
    1.59
    </h2>
    1.59
    ipzig
    1.58
    </td>
    1.55
    嗗
    1.55
    
    1.54
    meteries
    1.52
    Activations Density 0.052%

    No Known Activations