© 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. 123969
    Prev
    Next
    INDEX
    Explanations

    Necromancer, Subscribe, None

    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
     kering
    -1.70
     jeg
    -1.67
     maar
    -1.61
     butik
    -1.57
     Kompet
    -1.53
     poudre
    -1.48
     forêts
    -1.48
     flink
    -1.45
    </>
    -1.45
     andra
    -1.41
    POSITIVE LOGITS
     there
    1.77
     terdapat
    1.71
     too
    1.57
     promozione
    1.56
     debería
    1.56
     dianggap
    1.53
     shouldn
    1.49
     mancanza
    1.46
     Should
    1.45
    也不是
    1.44
    Activations Density 0.134%

    No Known Activations