© 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. 68373
    Prev
    Next
    INDEX
    Explanations

    description of action and objects

    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
     your
    -2.05
     you
    -1.67
    begin
    -1.51
     puedas
    -1.51
     podrás
    -1.47
     cualquier
    -1.46
    un
    -1.41
     that
    -1.39
     empez
    -1.39
    lerden
    -1.38
    POSITIVE LOGITS
     Conférence
    1.37
    ,
    1.36
    enfants
    1.30
     饼
    1.29
     to
    1.27
     dictionnaire
    1.27
     verwijzen
    1.26
    ndham
    1.26
     CONCEP
    1.24
     as
    1.23
    Activations Density 0.178%

    No Known Activations