© 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. 109654
    Prev
    Next
    INDEX
    Explanations

    specifier for object types

    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
    MEDIA
    -0.70
     pizzas
    -0.68
     Pharmaceutical
    -0.67
     Catt
    -0.67
    Clubs
    -0.66
     phòng
    -0.66
     воору
    -0.65
    __))
    -0.65
     bemerk
    -0.64
    Lorsque
    -0.63
    POSITIVE LOGITS
    obé
    0.73
     quốc
    0.68
    tagged
    0.67
    出し
    0.66
     temos
    0.64
     XXI
    0.64
    tutorial
    0.63
    auth
    0.63
    理智
    0.63
     Boko
    0.62
    Activations Density 0.062%

    No Known Activations