© 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. 113093
    Prev
    Next
    INDEX
    Explanations

    still available or active

    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
     reducción
    -1.30
     célè
    -1.29
    翾
    -1.23
     rempliss
    -1.23
    ╍
    -1.23
    
    -1.22
    lusst
    -1.22
    ditionally
    -1.21
     però
    -1.20
     glú
    -1.19
    POSITIVE LOGITS
     after
    1.47
     после
    1.30
    let
    1.21
    you
    1.13
    va
    1.11
     dopo
    1.11
     in
    1.08
    se
    1.05
    *********/
    1.04
    ou
    1.02
    Activations Density 0.048%

    No Known Activations