© 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. 19689
    Prev
    Next
    INDEX
    Explanations

    let, two, three, four, five, seven

    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
     utiliser
    -2.14
     Eſ
    -1.84
     ingenieros
    -1.82
     viſ
    -1.82
     deſt
    -1.77
     ſer
    -1.75
     zapato
    -1.72
    鲮
    -1.72
     pantalón
    -1.71
    acją
    -1.71
    POSITIVE LOGITS
     two
    2.69
     three
    2.55
     with
    2.48
     from
    2.22
     more
    2.17
     just
    2.17
     five
    2.11
     seven
    2.11
     four
    2.09
     went
    2.03
    Activations Density 0.024%

    No Known Activations