© 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. 10-GEMMASCOPE-RES-131K
    7. 69746
    Prev
    Next
    INDEX
    Explanations

    filled with something

    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
     medier
    -1.49
     przede
    -1.47
     nachts
    -1.43
     måneder
    -1.41
     bedankt
    -1.41
    讓你
    -1.40
     you
    -1.39
    齁
    -1.38
     souri
    -1.37
     rappelle
    -1.35
    POSITIVE LOGITS
     and
    1.78
     after
    1.56
     [
    1.27
     because
    1.24
     a
    1.21
    becue
    1.20
     but
    1.14
     two
    1.13
     никаких
    1.13
    водов
    1.12
    Activations Density 0.008%

    No Known Activations