© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106702
    Prev
    Next
    INDEX
    Explanations

    Q: or Company Stock

    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_34/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
    anten
    -0.87
     Schuld
    -0.84
     swung
    -0.75
     segu
    -0.73
    Coppa
    -0.70
    strictEqual
    -0.70
     tied
    -0.70
     Labrador
    -0.69
     Canada
    -0.68
    defaults
    -0.66
    POSITIVE LOGITS
     remplissage
    0.81
     Ryanair
    0.80
     vétérina
    0.80
     béton
    0.79
     chirurgie
    0.79
    leroi
    0.79
     Niles
    0.76
     jei
    0.76
    PCell
    0.76
    bahar
    0.75
    Activations Density 0.009%

    No Known Activations