© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91016
    Prev
    Next
    INDEX
    Explanations

    patent, number, or link

    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
    Warna
    -1.16
    Cinta
    -1.13
    Kolor
    -1.10
    Buat
    -1.09
    Jalan
    -1.06
    Imágenes
    -1.05
    Waga
    -1.04
    Rumah
    -1.03
    kleine
    -1.02
    Wady
    -1.00
    POSITIVE LOGITS
    V
    1.04
    T
    1.02
    []
    0.98
    Read
    0.96
    [
    0.94
    AS
    0.94
    ज
    0.94
    M
    0.93
    Click
    0.93
    B
    0.93
    Activations Density 0.001%

    No Known Activations