© 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. 32672
    Prev
    Next
    INDEX
    Explanations

    predicting questions and articles

    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
     of
    -1.16
     will
    -1.01
     a
    -0.93
     one
    -0.88
     would
    -0.86
    striped
    -0.85
     from
    -0.85
     last
    -0.83
     or
    -0.81
     neue
    -0.81
    POSITIVE LOGITS
     coû
    1.13
     dát
    1.13
     škole
    1.00
     connaissent
    0.99
    הגב
    0.98
    высо
    0.97
     hudeb
    0.97
     diariamente
    0.96
    entendre
    0.96
    也沒有
    0.94
    Activations Density 0.006%

    No Known Activations