© 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. 58044
    Prev
    Next
    INDEX
    Explanations

    product followed by details

    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
     they
    -2.42
     were
    -2.02
     you
    -1.91
     that
    -1.91
     but
    -1.90
     we
    -1.88
     At
    -1.80
    ꦁ
    -1.79
    三月
    -1.77
    星辰
    -1.77
    POSITIVE LOGITS
     Einfluß
    1.90
    als
    1.89
    2
    1.86
     vollständige
    1.80
    \
    1.79
    3
    1.79
     \
    1.76
    5
    1.76
    '
    1.76
    ただの
    1.75
    Activations Density 0.013%

    No Known Activations