© 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. 64484
    Prev
    Next
    INDEX
    Explanations

    the followed by a noun

    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
     how
    -1.66
     viewWillAppear
    -1.51
     whether
    -1.38
    それにしても
    -1.36
     what
    -1.34
    ouncements
    -1.30
     robić
    -1.30
     segera
    -1.26
     in
    -1.25
    estros
    -1.24
    POSITIVE LOGITS
     they
    1.86
     completion
    1.58
     anfangen
    1.34
     publication
    1.32
     we
    1.28
     inception
    1.27
     remporté
    1.27
    狨
    1.16
     last
    1.14
     onset
    1.12
    Activations Density 0.039%

    No Known Activations