© 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. 111687
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and modals like 'could be'

    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
     devraient
    -1.46
    枼
    -1.18
    olving
    -1.17
    تما
    -1.17
    mostly
    -1.16
    possible
    -1.16
     chwili
    -1.15
     Refs
    -1.14
    thmus
    -1.13
    苼
    -1.13
    POSITIVE LOGITS
     there
    1.47
     it
    1.35
     then
    1.28
     just
    1.26
     what
    1.15
    ");
    1.10
    enggarakan
    1.09
     dozens
    1.06
     strong
    1.02
     там
    1.02
    Activations Density 0.047%

    No Known Activations