© 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. 77025
    Prev
    Next
    INDEX
    Explanations

    image paths and urls

    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
     ticket
    -0.80
     mussten
    -0.71
    衛隊
    -0.69
    になりますが
    -0.69
     Ticket
    -0.68
     durfte
    -0.68
    zzati
    -0.67
     PubMed
    -0.67
    /?
    -0.65
     FACTS
    -0.65
    POSITIVE LOGITS
     images
    3.52
    images
    3.08
    img
    2.97
     img
    2.83
     image
    2.61
     Images
    2.53
    Images
    2.42
    imgs
    2.27
     pictures
    2.27
     imagery
    2.23
    Activations Density 0.021%

    No Known Activations