© 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. 16771
    Prev
    Next
    INDEX
    Explanations

    pm timestamps

    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
    seamnă
    -1.27
     artikkelen
    -1.15
    Normdaten
    -1.13
    édie
    -1.05
     utaf
    -1.05
     However
    -1.05
     inaweza
    -1.04
    一会儿
    -1.03
     But
    -1.02
     lakini
    -1.02
    POSITIVE LOGITS
    Medidas
    1.17
    Anzeige
    1.13
    Übernach
    1.13
    Keterangan
    1.13
    Bjs
    1.09
    Kontra
    1.09
    figurine
    1.09
    pineapple
    1.09
    Puntos
    1.08
    Pilih
    1.08
    Activations Density 0.013%

    No Known Activations