© 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. 127989
    Prev
    Next
    INDEX
    Explanations

    ip addresses

    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
    A
    -1.64
     By
    -1.59
     A
    -1.43
    P
    -1.42
     So
    -1.41
    S
    -1.35
     You
    -1.34
     To
    -1.30
    L
    -1.30
     But
    -1.29
    POSITIVE LOGITS
     célè
    1.41
    舳
    1.34
     répon
    1.34
    Frage
    1.33
    Karakter
    1.30
     plafon
    1.30
    Makanan
    1.29
    变成了
    1.27
     organik
    1.27
    titial
    1.26
    Activations Density 0.008%

    No Known Activations