© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22605
    Prev
    Next
    INDEX
    Explanations

    reporting research data

    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
    Negative Logits
     your
    -1.91
     тебя
    -1.41
     hectáreas
    -1.34
     einzelnen
    -1.28
     you
    -1.28
     encuentran
    -1.27
     already
    -1.26
    wijze
    -1.26
    就可以了
    -1.26
     lanzó
    -1.24
    POSITIVE LOGITS
    她
    1.50
    </em>
    1.43
    АН
    1.42
     ['./
    1.41
    Seeing
    1.38
     ""],
    1.35
     IMPLIED
    1.34
    зывает
    1.32
    первых
    1.26
    енно
    1.25
    Activations Density 0.544%

    No Known Activations