© 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. 67254
    Prev
    Next
    INDEX
    Explanations

    critical success or praise

    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
     Some
    -2.14
     Recently
    -2.11
     Those
    -1.89
     ehemaligen
    -1.88
     Another
    -1.87
     Maybe
    -1.85
     Anyone
    -1.85
     Several
    -1.82
     Something
    -1.79
     There
    -1.77
    POSITIVE LOGITS
     THOUGH
    2.02
     penghar
    1.69
     satria
    1.66
     BRITISH
    1.66
    libatkan
    1.66
     REASONS
    1.66
     aussit
    1.66
     olie
    1.65
     nocy
    1.64
     estadounid
    1.63
    Activations Density 0.008%

    No Known Activations