© 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. 11983
    Prev
    Next
    INDEX
    Explanations

    who/all/everyone addressed

    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
     two
    -2.16
     a
    -1.72
     three
    -1.57
     four
    -1.54
     vermutlich
    -1.42
    because
    -1.38
     poderosa
    -1.33
     eight
    -1.32
     ziemlich
    -1.30
     solution
    -1.30
    POSITIVE LOGITS
     of
    1.72
     intermedia
    1.69
    颪
    1.60
    <bos>
    1.58
    茈
    1.54
    ことから
    1.49
    бами
    1.49
    袿
    1.48
    şem
    1.46
    蔟
    1.44
    Activations Density 0.009%

    No Known Activations