© 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. 23540
    Prev
    Next
    INDEX
    Explanations

    court submissions

    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
    Intersection
    -0.76
    irmed
    -0.75
     pwd
    -0.70
    がいい
    -0.69
    アメ
    -0.69
    listado
    -0.67
    bobox
    -0.66
    std
    -0.66
    pan
    -0.65
    articulo
    -0.65
    POSITIVE LOGITS
    Took
    0.81
    ibrary
    0.74
    ációs
    0.70
     Kissinger
    0.70
    Vegan
    0.69
    yog
    0.68
     ExecuteAsync
    0.68
    hingga
    0.68
    arande
    0.68
     صغير
    0.67
    Activations Density 0.073%

    No Known Activations