© 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. 68625
    Prev
    Next
    INDEX
    Explanations

    convex optimization and analysis

    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
    }
    -2.17
    of
    -2.08
    .”
    -2.05
    d
    -2.05
    」(
    -2.03
     principi
    -2.00
    a
    -1.95
     внешний
    -1.91
    h
    -1.91
    逦
    -1.90
    POSITIVE LOGITS
    \
    2.52
     моя
    2.47
     哪些
    2.25
     και
    2.20
    寕
    2.17
     哪
    2.14
    䉴
    2.11
    ‪.‬‬
    2.11
     और
    2.02
     silencioso
    2.00
    Activations Density 0.004%

    No Known Activations