© 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. 43984
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and notation

    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
     ultimi
    -1.59
     Dinas
    -1.58
     Eröffnung
    -1.57
    k
    -1.53
     THOSE
    -1.52
    sibirsk
    -1.52
    させて頂
    -1.46
     или
    -1.45
    irmanship
    -1.44
    larınız
    -1.43
    POSITIVE LOGITS
     also
    1.94
     more
    1.81
     auch
    1.70
    ViewChild
    1.60
     not
    1.60
     také
    1.53
     aussi
    1.53
     Also
    1.50
    …"
    1.49
    秝
    1.48
    Activations Density 0.016%

    No Known Activations