© 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. 20440
    Prev
    Next
    INDEX
    Explanations

    roles of creators and managers

    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
     بأنه
    -1.48
     where
    -1.36
     we
    -1.25
     跳转至
    -1.20
     you
    -1.18
     aufgrund
    -1.12
    gencias
    -1.11
    ␮
    -1.11
    ≲
    -1.11
    ocarp
    -1.09
    POSITIVE LOGITS
    kệ
    1.32
    Bản
    1.29
    layın
    1.26
    ٧
    1.23
    šas
    1.23
     yoksa
    1.19
     objekt
    1.16
    っていたので
    1.14
    ofing
    1.14
     one
    1.14
    Activations Density 0.075%

    No Known Activations