© 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. 43001
    Prev
    Next
    INDEX
    Explanations

    code and concepts

    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
     Segel
    -1.13
    droj
    -1.13
     and
    -1.12
    Origine
    -1.11
     хотя
    -1.06
     they
    -1.05
    dene
    -1.04
     píše
    -1.00
    pneu
    -0.99
     tämä
    -0.98
    POSITIVE LOGITS
    ment
    1.39
    lique
    1.33
    InputBorder
    1.28
    '){
    1.27
    OrNil
    1.25
    !");
    1.24
    romas
    1.23
    +"'
    1.23
     <",
    1.23
    lia
    1.21
    Activations Density 0.536%

    No Known Activations