© 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. 66014
    Prev
    Next
    INDEX
    Explanations

    International Biennial, Biennale, Competition

    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
    ļas
    -0.77
     inflationary
    -0.77
    テト
    -0.73
    稲
    -0.73
    機關
    -0.72
     SEDS
    -0.70
    ddot
    -0.70
     waisted
    -0.70
    ceği
    -0.69
     diving
    -0.69
    POSITIVE LOGITS
     bien
    1.59
    Bien
    1.59
     Bien
    1.32
     Biennial
    1.23
    bien
    1.23
     Biennale
    1.16
     biennial
    1.15
     Venice
    0.96
    curated
    0.92
     BIEN
    0.90
    Activations Density 0.011%

    No Known Activations