© 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. 10-GEMMASCOPE-RES-131K
    7. 22488
    Prev
    Next
    INDEX
    Explanations

    NF-κB, Javascript, primitives

    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_10/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
     Absicht
    -1.63
     drenaje
    -1.63
     Bedürf
    -1.57
     Auffassung
    -1.55
     provenientes
    -1.52
     escaleras
    -1.46
     acogedor
    -1.46
     aceste
    -1.46
     Verpflich
    -1.45
     necessária
    -1.44
    POSITIVE LOGITS
     in
    2.42
     to
    1.97
    -
    1.41
     into
    1.38
    
    1.25
    "
    1.24
    (;;)
    1.23
    do
    1.21
     for
    1.20
    сно
    1.19
    Activations Density 0.003%

    No Known Activations