© 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. 99620
    Prev
    Next
    INDEX
    Explanations

    nearly over

    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
     manuelle
    -1.32
     familières
    -1.29
    鶿
    -1.28
    dits
    -1.26
     élevées
    -1.24
     entregó
    -1.23
     and
    -1.23
     conç
    -1.22
    els
    -1.21
     ženy
    -1.20
    POSITIVE LOGITS
     all
    1.77
     ended
    1.46
     this
    1.46
     another
    1.41
     over
    1.41
     whose
    1.38
     which
    1.37
     when
    1.35
     had
    1.34
     same
    1.34
    Activations Density 0.018%

    No Known Activations