© 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. 34-GEMMASCOPE-RES-131K
    7. 77776
    Prev
    Next
    INDEX
    Explanations

    under, younger, older, above

    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_34/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
    邈
    -0.74
     Patience
    -0.73
     constrained
    -0.71
     asympto
    -0.71
     превра
    -0.69
    套
    -0.68
     noi
    -0.68
    endan
    -0.67
    ћи
    -0.67
    CancelButton
    -0.67
    POSITIVE LOGITS
     under
    2.52
    Under
    2.03
    under
    2.03
     Under
    1.84
     UNDER
    1.48
    UNDER
    1.44
     dưới
    1.34
     под
    1.34
     bajo
    1.32
     onder
    1.17
    Activations Density 0.060%

    No Known Activations