© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99563
    Prev
    Next
    INDEX
    Explanations

    transportation and agents

    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
     akce
    -1.39
     Six
    -1.26
     esclavos
    -1.25
     Down
    -1.24
     Working
    -1.21
     extraordinario
    -1.21
     into
    -1.20
     Black
    -1.17
     boletín
    -1.17
    FormGroup
    -1.16
    POSITIVE LOGITS
    塒
    1.27
     libera
    1.23
     хочет
    1.23
     historial
    1.20
     toti
    1.18
     любит
    1.18
     Pria
    1.17
     comanda
    1.17
     turtleneck
    1.17
     мужчина
    1.17
    Activations Density 0.075%

    No Known Activations