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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86411
    Prev
    Next
    INDEX
    Explanations

    gun control reform

    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
     there
    -2.27
     these
    -1.95
     other
    -1.73
     when
    -1.68
     Allí
    -1.57
     There
    -1.55
     Lainnya
    -1.50
     various
    -1.49
     bereits
    -1.49
     там
    -1.48
    POSITIVE LOGITS
     Etat
    1.36
     continually
    1.32
     FRANCE
    1.28
     projeto
    1.25
    ffichage
    1.24
    だったが
    1.23
     게임
    1.22
    ціона
    1.20
    zones
    1.19
    стить
    1.19
    Activations Density 0.105%

    No Known Activations