© 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. 38292
    Prev
    Next
    INDEX
    Explanations

    all-time records

    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
     templado
    -0.81
     marketed
    -0.74
    typeparam
    -0.69
    ::<
    -0.68
    cento
    -0.67
    蛀
    -0.66
     hashlib
    -0.66
     اپل
    -0.65
    íficos
    -0.64
     convened
    -0.64
    POSITIVE LOGITS
     time
    3.19
    time
    2.53
    TIME
    2.13
    Time
    2.02
     Time
    1.91
     TIME
    1.84
     времени
    1.76
     tiempo
    1.53
     время
    1.47
    getTime
    1.44
    Activations Density 0.024%

    No Known Activations