© 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. 32696
    Prev
    Next
    INDEX
    Explanations

    by [name/identifier]

    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
     galeri
    -1.32
     koning
    -1.16
     ül
    -1.15
     nabi
    -1.14
     pistolet
    -1.11
    ванович
    -1.09
     Frankrijk
    -1.09
     kredi
    -1.09
     TAMBÉM
    -1.09
     directora
    -1.08
    POSITIVE LOGITS
     someone
    1.21
     aptly
    1.16
     also
    1.12
     simply
    1.09
     ativar
    1.08
     have
    1.07
     appropriately
    1.04
     смотря
    1.02
     always
    1.02
     only
    1.02
    Activations Density 0.008%

    No Known Activations