© 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. 59568
    Prev
    Next
    INDEX
    Explanations

    string variables

    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
    </h4>
    -2.55
    liegenden
    -1.74
    𨭆
    -1.68
    </b>
    -1.67
    </sup>
    -1.66
    糁
    -1.58
    entwick
    -1.53
     jätte
    -1.52
    妡
    -1.51
    皛
    -1.48
    POSITIVE LOGITS
    阿姨
    1.72
    лению
    1.69
    ～～～
    1.63
    真好
    1.63
     When
    1.63
    ～～～～
    1.63
     pretože
    1.63
     zawsze
    1.56
     Throughout
    1.52
     to
    1.50
    Activations Density 0.029%

    No Known Activations