© 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. 22-GEMMASCOPE-RES-131K
    7. 15725
    Prev
    Next
    INDEX
    Explanations

    programming keywords or values

    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_22/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
    龊
    -1.07
     famed
    -1.06
     dando
    -1.05
     entusias
    -1.05
     malha
    -1.03
     privacidade
    -1.03
    ܬ
    -1.02
     condomínio
    -1.01
    brian
    -1.00
    おきます
    -1.00
    POSITIVE LOGITS
     or
    1.80
     then
    1.41
    或者是
    1.23
    گي
    1.15
    ':
    1.05
     this
    1.05
     entonces
    1.04
    两者
    1.04
    或是
    1.01
    ĭ
    1.01
    Activations Density 0.012%

    No Known Activations