© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11254
    Prev
    Next
    INDEX
    Explanations

    code and Portuguese words

    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
     lengthy
    -0.90
     droog
    -0.83
     begy
    -0.82
     this
    -0.81
     haberse
    -0.80
     Lowry
    -0.80
     charity
    -0.80
    hien
    -0.80
     from
    -0.79
     dobra
    -0.79
    POSITIVE LOGITS
     until
    0.96
     vários
    0.96
     várias
    0.93
     versões
    0.90
     epist
    0.90
     unveils
    0.85
     evolve
    0.82
     Until
    0.82
    até
    0.81
     configurações
    0.79
    Activations Density 0.007%

    No Known Activations