© 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. 65779
    Prev
    Next
    INDEX
    Explanations

    of the

    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
     also
    -1.71
     about
    -1.68
     vanske
    -1.47
     xxiii
    -1.42
    ־ה
    -1.41
    妺
    -1.38
     technically
    -1.35
     monumento
    -1.34
    °/
    -1.34
     xxvi
    -1.34
    POSITIVE LOGITS
     rồi
    1.47
     такие
    1.36
     ”
    1.36
     .
    1.30
     następnie
    1.21
    我們
    1.21
    }{||
    1.18
    鍙
    1.17
     такой
    1.17
     tiveram
    1.16
    Activations Density 0.079%

    No Known Activations