© 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. 85688
    Prev
    Next
    INDEX
    Explanations

    verbs and continuations

    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
     our
    -1.64
     an
    -1.52
     on
    -1.48
     we
    -1.46
     for
    -1.45
     a
    -1.41
     any
    -1.38
     themselves
    -1.36
     unsere
    -1.34
     so
    -1.30
    POSITIVE LOGITS
    ᐈ
    1.29
     Motos
    1.28
     endgül
    1.28
    ಱ
    1.28
     allmäh
    1.27
     finalmente
    1.24
    訁
    1.24
     unveils
    1.23
     vorüber
    1.22
    ਗ਼
    1.22
    Activations Density 0.038%

    No Known Activations