© 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. 84176
    Prev
    Next
    INDEX
    Explanations

    street numbers, times, addresses

    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
    här
    -1.91
     mépris
    -1.70
    　　[
    -1.70
     sécher
    -1.66
    حوال
    -1.62
    fatter
    -1.61
    شاهد
    -1.60
    葙
    -1.59
    Garantie
    -1.59
    ței
    -1.58
    POSITIVE LOGITS
    id
    1.79
    v
    1.74
    ot
    1.69
    ch
    1.64
    h
    1.62
    ma
    1.59
    ver
    1.57
    ul
    1.55
    w
    1.55
    en
    1.49
    Activations Density 0.026%

    No Known Activations