© 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. 16469
    Prev
    Next
    INDEX
    Explanations

    programming language identifiers and keywords

    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
    Not in Any Lists

    No Comments

    Negative Logits
    の人に
    -1.13
    はな
    -1.06
    fromLTRB
    -1.01
    の概要
    -1.01
     acidente
    -1.01
    の方も
    -1.00
    Ucraina
    -0.98
     popolari
    -0.97
    の方に
    -0.97
     sexuales
    -0.97
    POSITIVE LOGITS
     pia
    1.16
    Wien
    1.16
     stylo
    1.13
     piec
    1.11
     AKP
    1.09
     huf
    1.06
     metropol
    1.06
    Ety
    1.05
     gara
    1.05
     cardin
    1.05
    Activations Density 0.000%

    No Known Activations