© 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. 21973
    Prev
    Next
    INDEX
    Explanations

    image tags ![]( )

    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
    .
    -1.73
    沨
    -1.55
    общение
    -1.36
     alemán
    -1.34
     alegre
    -1.34
     portugués
    -1.34
    ugais
    -1.34
    :
    -1.33
     reciente
    -1.32
    ったり
    -1.27
    POSITIVE LOGITS
     it
    1.66
     have
    1.58
    它是
    1.48
    🥴
    1.37
    它
    1.27
     will
    1.21
     originated
    1.20
     모든
    1.20
    它的
    1.19
    ，”
    1.19
    Activations Density 0.039%

    No Known Activations