© 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. 34-GEMMASCOPE-RES-131K
    7. 84477
    Prev
    Next
    INDEX
    Explanations

    average or median 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_34/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
     numbered
    -0.87
     soggetti
    -0.85
     until
    -0.83
     rischi
    -0.80
     épocas
    -0.78
    .~
    -0.78
    сіб
    -0.77
    (?
    -0.77
    予告
    -0.77
     erlauben
    -0.77
    POSITIVE LOGITS
     median
    1.84
     average
    1.67
    median
    1.55
    Median
    1.52
     Average
    1.40
    Average
    1.34
     Median
    1.32
    AVERAGE
    1.29
     śred
    1.23
     mediana
    1.20
    Activations Density 0.022%

    No Known Activations