© 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. 22-GEMMASCOPE-RES-131K
    7. 16719
    Prev
    Next
    INDEX
    Explanations

    leading provider or leader

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    :
    -1.45
     those
    -1.45
     even
    -1.41
     навіть
    -1.40
     that
    -1.39
     these
    -1.36
    散策
    -1.32
     what
    -1.29
    🩱
    -1.26
     both
    -1.25
    POSITIVE LOGITS
    అ
    1.31
    ఒ
    1.30
     pintar
    1.23
    ఉ
    1.20
    ఇ
    1.16
    aní
    1.13
     альбом
    1.13
    rescence
    1.13
     levier
    1.13
     délai
    1.10
    Activations Density 0.042%

    No Known Activations