© 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. 39900
    Prev
    Next
    INDEX
    Explanations

    +/- range or deviation

    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
    <em>
    -2.55
    躥
    -2.52
    ſſen
    -2.42
    廰
    -2.41
    </h4>
    -2.39
    獃
    -2.34
    书房
    -2.31
    秝
    -2.27
    嚶
    -2.20
    ">
    -2.06
    POSITIVE LOGITS
    Ᏺ
    2.69
    
    2.42
    苼
    2.39
    ႐
    2.38
    𐐀
    2.38
     feine
    2.34
    狨
    2.33
     offene
    2.25
    </i>
    2.23
     tief
    2.22
    Activations Density 0.005%

    No Known Activations