© 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. 22-GEMMASCOPE-RES-131K
    7. 27792
    Prev
    Next
    INDEX
    Explanations

    how to / according to / a

    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_22/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
     There
    -0.85
     багато
    -0.85
     розмі
    -0.82
     單
    -0.82
    新疆
    -0.80
     колек
    -0.79
    ובן
    -0.75
     nät
    -0.73
     abandoning
    -0.73
     Left
    -0.73
    POSITIVE LOGITS
    ;\
    0.97
    ({\
    0.97
     ListNode
    0.93
    輟
    0.93
    tagHelper
    0.88
     hunde
    0.86
    Trichloroethane
    0.85
    ColumnHeaders
    0.85
    vás
    0.85
     cahaya
    0.84
    Activations Density 0.004%

    No Known Activations