© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20312
    Prev
    Next
    INDEX
    Explanations

    function, array, element, text

    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
    %
    -1.65
    })}\
    -1.64
    }
    -1.59
    *
    -1.56
    <i>
    -1.55
    如
    -1.55
    foundland
    -1.55
    #
    -1.53
    entown
    -1.52
    </b>
    -1.48
    POSITIVE LOGITS
     for
    1.88
     ещё
    1.70
    したのが
    1.57
    下一篇
    1.47
    trauer
    1.42
     that
    1.42
     prépare
    1.38
    ˽
    1.38
    ますが
    1.37
    形の
    1.33
    Activations Density 0.022%

    No Known Activations