© 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. 73613
    Prev
    Next
    INDEX
    Explanations

    get then method names

    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
     then
    -2.09
     on
    -2.03
     we
    -2.02
     with
    -1.83
     change
    -1.80
     by
    -1.80
     very
    -1.77
     there
    -1.72
     really
    -1.71
     naudoti
    -1.69
    POSITIVE LOGITS
     célè
    1.93
    
    1.83
     diriger
    1.76
     siè
    1.76
    
    1.70
     brune
    1.70
     soulign
    1.68
    蓠
    1.63
     !!!!
    1.59
    裃
    1.59
    Activations Density 0.020%

    No Known Activations