© 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. 15670
    Prev
    Next
    INDEX
    Explanations

    code syntax and keywords

    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
    睃
    -1.84
    ཿ
    -1.79
     semelh
    -1.64
    奁
    -1.63
     唯美
    -1.58
     praticamente
    -1.57
    derdag
    -1.56
     mauva
    -1.53
    袛
    -1.53
    釭
    -1.51
    POSITIVE LOGITS
     at
    2.42
     brings
    1.80
     of
    1.64
    ),
    1.63
     enormous
    1.62
     spurred
    1.59
     makes
    1.57
     gives
    1.56
     offers
    1.54
     flawless
    1.52
    Activations Density 0.018%

    No Known Activations