© 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. 10-GEMMASCOPE-RES-131K
    7. 128143
    Prev
    Next
    INDEX
    Explanations

    dead bolted, integrate well

    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
     that
    -2.11
     già
    -2.08
     it
    -1.80
     (
    -1.76
     these
    -1.70
     those
    -1.65
     you
    -1.63
    那些
    -1.62
    那个
    -1.52
    這些
    -1.50
    POSITIVE LOGITS
     Igreja
    1.89
     doña
    1.86
    ᳝
    1.78
    Особенности
    1.76
     pousada
    1.72
    انظر
    1.66
     chefe
    1.63
     reikia
    1.61
     savu
    1.61
     Água
    1.60
    Activations Density 0.118%

    No Known Activations