© 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. 75406
    Prev
    Next
    INDEX
    Explanations

    you don't want or need

    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
    -1.65
    (
    -1.63
    蹀
    -1.62
    怱
    -1.59
    宬
    -1.55
     hecta
    -1.51
     maten
    -1.49
    </b>
    -1.48
    呖
    -1.47
     valde
    -1.46
    POSITIVE LOGITS
     need
    1.77
     must
    1.73
     mieste
    1.70
     šo
    1.69
     måste
    1.67
     sesuatu
    1.66
     musíte
    1.66
     behov
    1.63
     koniecz
    1.63
     to
    1.63
    Activations Density 0.032%

    No Known Activations