© 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. 64513
    Prev
    Next
    INDEX
    Explanations

    what happens with THESE:

    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
     more
    -1.68
     or
    -1.58
     if
    -1.46
     завдання
    -1.35
     some
    -1.32
     no
    -1.32
     //
    -1.30
     not
    -1.30
     at
    -1.27
     their
    -1.27
    POSITIVE LOGITS
     grati
    1.57
     vermel
    1.56
     bensin
    1.45
     lucu
    1.44
     kado
    1.43
     teknis
    1.41
     kemer
    1.41
     comté
    1.41
     sanno
    1.41
     seksi
    1.40
    Activations Density 0.035%

    No Known Activations