© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1073
    Prev
    Next
    INDEX
    Explanations

    law and legal citations

    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
    yfikacja
    -0.81
    éral
    -0.76
    ccion
    -0.75
     カップ
    -0.75
     gây
    -0.70
    Kelebihan
    -0.70
    emate
    -0.70
    ramienta
    -0.70
    картинка
    -0.69
    ˧
    -0.69
    POSITIVE LOGITS
     symposium
    0.86
    springen
    0.84
     complementos
    0.83
     law
    0.80
    Especies
    0.76
     färg
    0.76
     forum
    0.75
     flagship
    0.75
    ONLINE
    0.75
     Law
    0.74
    Activations Density 0.032%

    No Known Activations