© 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. 37970
    Prev
    Next
    INDEX
    Explanations

    French titles and places

    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
     dieselben
    -0.84
    }$.\\
    -0.84
     mieszkańców
    -0.80
    それにしても
    -0.79
     zvyš
    -0.78
     повышение
    -0.75
    тивные
    -0.75
     los
    -0.75
     것이다
    -0.75
     debacle
    -0.72
    POSITIVE LOGITS
    ício
    0.99
    yentes
    0.90
    felizmente
    0.88
    ilibr
    0.86
    なのは
    0.85
     Isles
    0.85
     Pear
    0.84
     bahagia
    0.84
    heses
    0.82
    lably
    0.81
    Activations Density 0.016%

    No Known Activations