© 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. 10-GEMMASCOPE-RES-131K
    7. 87331
    Prev
    Next
    INDEX
    Explanations

    academic and research institutions

    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_10/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
    '
    -2.53
    1
    -1.91
     normalen
    -1.89
    Leírás
    -1.87
     ewigen
    -1.78
     grossen
    -1.77
     produisent
    -1.77
     falschen
    -1.71
     leeren
    -1.70
     dunklen
    -1.70
    POSITIVE LOGITS
     confronti
    1.63
     who
    1.59
     deutsch
    1.58
    一系列
    1.58
     allowing
    1.57
     all
    1.57
     ensuring
    1.57
    šu
    1.55
    ₁)
    1.47
    ｄ
    1.45
    Activations Density 0.067%

    No Known Activations