© 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. 21606
    Prev
    Next
    INDEX
    Explanations

    places or events

    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
     they
    -1.86
     while
    -1.66
     use
    -1.54
     September
    -1.51
     November
    -1.48
     June
    -1.45
    <blockquote>
    -1.43
     as
    -1.41
     millon
    -1.38
     December
    -1.38
    POSITIVE LOGITS
     飯店
    1.72
     Vergnügen
    1.58
     viviendas
    1.55
     トラベル
    1.53
    躂
    1.52
    гії
    1.51
     読む
    1.49
     廠
    1.46
    豋
    1.45
    Библи
    1.43
    Activations Density 0.025%

    No Known Activations