© 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. 127970
    Prev
    Next
    INDEX
    Explanations

    code structure

    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
    }$
    -2.56
    <td>
    -1.91
    </sub>
    -1.75
    一流
    -1.71
    </u>
    -1.71
    創造
    -1.70
    ция
    -1.69
    к
    -1.69
    </code>
    -1.67
    不过
    -1.65
    POSITIVE LOGITS
    ,…
    2.13
    她也
    2.06
     […]
    1.90
    ((&
    1.88
    眼下
    1.88
     şimdi
    1.85
    錀
    1.77
    欤
    1.75
     classed
    1.74
     (…)
    1.73
    Activations Density 0.002%

    No Known Activations