© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 49966
    Prev
    Next
    INDEX
    Explanations

    code syntax and identifiers

    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
    ʄ
    -0.73
    嘸
    -0.71
    Ej
    -0.69
     chestnut
    -0.69
    廪
    -0.69
     Warrant
    -0.69
     厂家
    -0.68
     terri
    -0.68
     häufiger
    -0.68
     volunte
    -0.67
    POSITIVE LOGITS
     second
    0.87
     begin
    0.77
     latter
    0.75
     thập
    0.72
     References
    0.71
     incremental
    0.71
    mtp
    0.70
    جت
    0.70
     Fast
    0.70
     Config
    0.70
    Activations Density 0.025%

    No Known Activations