© 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. 127238
    Prev
    Next
    INDEX
    Explanations

    see how

    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
     Another
    -1.80
    ützen
    -1.68
     Somebody
    -1.68
     How
    -1.63
     لدي
    -1.60
     Finally
    -1.59
     Publicar
    -1.59
    があると
    -1.58
     Why
    -1.57
     Acuerdo
    -1.55
    POSITIVE LOGITS
     through
    1.58
    衚
    1.55
    ot
    1.52
     it
    1.47
    盌
    1.43
    塒
    1.41
    鬭
    1.41
    袿
    1.39
    唷
    1.39
     albeit
    1.34
    Activations Density 0.009%

    No Known Activations