© 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. 59464
    Prev
    Next
    INDEX
    Explanations

    number of repetitions

    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
     “[
    -1.84
     “(
    -1.81
    まったく
    -1.62
     größ
    -1.58
    —”
    -1.53
     realmente
    -1.50
    全く
    -1.50
     lenge
    -1.41
     cheia
    -1.41
    事も
    -1.41
    POSITIVE LOGITS
     in
    2.06
    ,"
    1.66
    u
    1.63
    ")
    1.62
    omorphisms
    1.60
    there
    1.57
    ेमाल
    1.55
    rī
    1.55
    vierung
    1.54
    Контак
    1.52
    Activations Density 0.013%

    No Known Activations