© 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. 14397
    Prev
    Next
    INDEX
    Explanations

    enter to win

    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
     lanka
    -1.84
     violon
    -1.79
     soldat
    -1.75
     vernac
    -1.74
    
    -1.66
     formant
    -1.65
     luxem
    -1.64
    ︕
    -1.64
     ?
    -1.60
     achat
    -1.59
    POSITIVE LOGITS
     not
    1.84
     to
    1.77
     on
    1.68
     only
    1.64
     for
    1.64
     any
    1.62
     either
    1.59
     between
    1.58
     even
    1.57
     While
    1.56
    Activations Density 0.033%

    No Known Activations