© 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. 43774
    Prev
    Next
    INDEX
    Explanations

    parenthesized non-english words

    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
     to
    -1.71
     a
    -1.49
     misschien
    -1.33
     påver
    -1.30
     ſont
    -1.24
    鹩
    -1.17
    噼
    -1.14
    DataTo
    -1.13
     insanların
    -1.13
    gih
    -1.10
    POSITIVE LOGITS
     there
    1.49
     who
    1.45
     you
    1.41
     genoux
    1.37
     της
    1.36
     Forder
    1.33
     derer
    1.32
    Olvid
    1.31
    frutar
    1.30
    ↵
    1.29
    Activations Density 0.324%

    No Known Activations