© 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. 128741
    Prev
    Next
    INDEX
    Explanations

    big and giant things

    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
     recibieron
    -1.32
     llevaron
    -1.31
     efectuar
    -1.29
     ocultar
    -1.27
    begin
    -1.26
     admitir
    -1.24
    tismo
    -1.23
    elett
    -1.22
    ,:]
    -1.21
    した場合
    -1.20
    POSITIVE LOGITS
     that
    1.71
     antici
    1.35
     were
    1.26
     coreano
    1.25
     samping
    1.23
     kuris
    1.20
     precau
    1.19
     camere
    1.18
     which
    1.17
    вую
    1.17
    Activations Density 0.049%

    No Known Activations