© 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. 22-GEMMASCOPE-RES-131K
    7. 14907
    Prev
    Next
    INDEX
    Explanations

    places and geographical features

    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_22/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
     оружи
    -1.69
     garansi
    -1.58
     you
    -1.58
     penjual
    -1.56
     farà
    -1.52
    ごめん
    -1.52
     different
    -1.50
     your
    -1.48
     will
    -1.47
     pelatih
    -1.47
    POSITIVE LOGITS
     últimas
    1.48
     decorativos
    1.36
    URLEncoder
    1.34
     ancienne
    1.31
     alimen
    1.29
     baloncesto
    1.27
    缰
    1.27
    zło
    1.26
     listop
    1.21
     maiores
    1.21
    Activations Density 0.018%

    No Known Activations