© 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. 16421
    Prev
    Next
    INDEX
    Explanations

    programming constructs and types

    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
     triko
    -1.38
     blusas
    -1.36
     radikal
    -1.35
     作り方
    -1.34
     camiset
    -1.34
    鱨
    -1.31
    Lokal
    -1.31
     実例
    -1.30
     kritik
    -1.30
     插图
    -1.27
    POSITIVE LOGITS
    c
    1.39
    f
    1.38
    p
    1.38
    T
    1.32
    g
    1.32
    F
    1.30
    M
    1.27
    h
    1.27
    qu
    1.26
    ll
    1.25
    Activations Density 0.015%

    No Known Activations