© 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. 14497
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers

    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
     appeler
    -1.79
     dezelfde
    -1.65
     suministros
    -1.58
     hetzelfde
    -1.54
     préciser
    -1.54
     mármol
    -1.51
     selben
    -1.47
     efectuar
    -1.44
     pourrait
    -1.43
     distinguer
    -1.42
    POSITIVE LOGITS
     in
    2.16
     over
    1.95
     other
    1.91
     because
    1.70
     out
    1.69
     with
    1.67
     since
    1.62
     through
    1.54
    $.
    1.53
     throughout
    1.51
    Activations Density 0.111%

    No Known Activations