© 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. 34-GEMMASCOPE-RES-131K
    7. 106266
    Prev
    Next
    INDEX
    Explanations

    precedes or follows

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     for
    -1.70
     this
    -1.52
     that
    -1.42
     at
    -1.28
     by
    -1.27
     but
    -1.26
     on
    -1.22
     when
    -1.13
     lavish
    -1.02
     then
    -0.98
    POSITIVE LOGITS
     predeceased
    1.66
     preceded
    1.52
     preceding
    1.44
     также
    1.17
     précé
    1.14
     preced
    1.13
     precede
    1.13
     préc
    1.12
     additionally
    1.12
     prédé
    1.10
    Activations Density 0.001%

    No Known Activations