© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7218
    Prev
    Next
    INDEX
    Explanations

    problem, achievements, station, promotion, applications

    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
     will
    -2.13
     it
    -1.68
     to
    -1.62
     lainnya
    -1.48
    дой
    -1.35
     bahkan
    -1.30
    無い
    -1.28
     sogar
    -1.27
     powietrza
    -1.26
    甚至
    -1.25
    POSITIVE LOGITS
     this
    1.67
    詬
    1.58
    più
    1.54
     groet
    1.52
    躋
    1.48
     such
    1.43
    嘮
    1.42
     everytime
    1.39
     apartament
    1.38
    够了
    1.34
    Activations Density 0.158%

    No Known Activations