© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11002
    Prev
    Next
    INDEX
    Explanations

    qualitative descriptions

    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
     that
    -1.88
     wszyst
    -1.69
     previously
    -1.61
     formerly
    -1.60
     wszyscy
    -1.57
     or
    -1.55
     already
    -1.50
     to
    -1.47
    >
    -1.45
     existing
    -1.41
    POSITIVE LOGITS
     way
    1.61
     olmak
    1.46
     lutego
    1.39
    umesc
    1.36
    (!__
    1.35
    リューション
    1.31
    مقال
    1.30
    Ако
    1.29
     soigneusement
    1.28
     приходит
    1.27
    Activations Density 0.045%

    No Known Activations