© 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. 58021
    Prev
    Next
    INDEX
    Explanations

    questions about boxes or screens

    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
     DURING
    -1.83
     paltry
    -1.61
     ludicrous
    -1.60
     vuur
    -1.54
     WHILE
    -1.52
     hapless
    -1.49
    珦
    -1.48
     jarring
    -1.46
     luscious
    -1.45
     tijdens
    -1.41
    POSITIVE LOGITS
     of
    1.98
    e
    1.94
     使っ
    1.75
    c
    1.73
    )$
    1.66
     эти
    1.63
    ENDIAN
    1.55
     systems
    1.55
    id
    1.52
     time
    1.52
    Activations Density 0.007%

    No Known Activations