© 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. 10-GEMMASCOPE-RES-131K
    7. 43299
    Prev
    Next
    INDEX
    Explanations

    on the basis of

    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
    ’
    -1.99
    ’”
    -1.75
     There
    -1.73
     was
    -1.70
    ’)
    -1.59
    缓慢
    -1.59
    我了
    -1.55
    ’).
    -1.53
     Our
    -1.52
    ựu
    -1.52
    POSITIVE LOGITS
    ad
    1.62
    他
    1.58
     duże
    1.55
     動物
    1.55
    f
    1.53
     nytt
    1.51
    k
    1.51
    ta
    1.51
    一个
    1.50
     البعض
    1.45
    Activations Density 0.011%

    No Known Activations