© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200983
    Prev
    Next
    INDEX
    Explanations

    towels, Egyptian, Awards, cleaning

    np_acts-logits-general · gemini-2.5-flash-lite

    boy, competition, certificates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     símbolo
    0.58
     Çok
    0.57
     símbolos
    0.57
    倖
    0.54
     İyi
    0.52
     Cortana
    0.52
    ého
    0.50
     Aş
    0.50
     開始
    0.50
     nó
    0.50
    POSITIVE LOGITS
    িয়াল
    0.48
    сеп
    0.46
     семьи
    0.46
    窑
    0.46
    Certificate
    0.43
    urbation
    0.43
    ginas
    0.43
     компанией
    0.43
    жением
    0.43
    moon
    0.42
    Activations Density 0.002%

    No Known Activations