© 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. 44762
    Prev
    Next
    INDEX
    Explanations

    article describes

    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
     profils
    -1.63
     miſ
    -1.61
     talleres
    -1.59
    鹪
    -1.55
     nettoy
    -1.55
     frança
    -1.54
    洐
    -1.53
    把它
    -1.53
    还是很
    -1.52
    ឬ
    -1.51
    POSITIVE LOGITS
     When
    1.88
    </h1>
    1.53
    '
    1.52
    </i>
    1.51
     to
    1.50
    mathrm
    1.48
    ));
    1.42
     various
    1.38
     both
    1.38
     o
    1.38
    Activations Density 0.020%

    No Known Activations