© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123694
    Prev
    Next
    INDEX
    Explanations

    Jewish people and associations

    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
     conformité
    -2.25
    可以说是
    -2.22
     nourriture
    -2.22
     uſed
    -2.22
    êncio
    -2.17
    の絵
    -2.17
     consommate
    -2.16
    となりました
    -2.16
    わから
    -2.14
     harten
    -2.14
    POSITIVE LOGITS
    姈
    2.98
    ness
    2.63
     ぼ
    2.58
    ly
    2.53
    стреча
    2.48
    '])
    2.42
    торая
    2.34
     entspre
    2.34
    媗
    2.31
    новь
    2.30
    Activations Density 0.005%

    No Known Activations