© 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. 49629
    Prev
    Next
    INDEX
    Explanations

    technical specifications and code definitions

    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
    Вла
    -0.78
    elfs
    -0.77
    دست
    -0.75
     patterning
    -0.74
    avelmente
    -0.73
     Khrushchev
    -0.71
    Rode
    -0.71
     Homecoming
    -0.71
    Ҭ
    -0.70
     valueForKey
    -0.70
    POSITIVE LOGITS
    cooler
    0.89
    を考えて
    0.82
    tub
    0.80
     színes
    0.77
     tuong
    0.77
    larla
    0.75
    Acces
    0.75
     martial
    0.74
    DataItem
    0.73
     kuno
    0.73
    Activations Density 0.001%

    No Known Activations