© 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. 22-GEMMASCOPE-RES-131K
    7. 15395
    Prev
    Next
    INDEX
    Explanations

    proven to be

    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_22/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
     tille
    -1.45
     huel
    -1.34
    ihnachts
    -1.32
     ferien
    -1.30
     uren
    -1.28
     etui
    -1.25
    hounds
    -1.23
    킵
    -1.23
     parachoque
    -1.23
     pleaf
    -1.23
    POSITIVE LOGITS
     be
    1.44
     to
    1.44
     with
    1.36
     by
    1.36
     [
    1.34
     
    1.32
    ,
    1.28
     ,
    1.27
     can
    1.27
     .
    1.26
    Activations Density 0.031%

    No Known Activations