© 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. 128016
    Prev
    Next
    INDEX
    Explanations

    code structure elements

    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
     all
    -1.45
     each
    -1.43
     any
    -1.40
     through
    -1.35
     with
    -1.34
     many
    -1.27
     every
    -1.27
     everyone
    -1.25
     their
    -1.24
     some
    -1.23
    POSITIVE LOGITS
     enlever
    1.21
    ？！”
    1.20
     skór
    1.19
     arrêter
    1.19
     consommer
    1.16
    If
    1.12
     écouter
    1.12
     nettoyer
    1.11
     délais
    1.10
     réinitial
    1.10
    Activations Density 0.001%

    No Known Activations