© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38225
    Prev
    Next
    INDEX
    Explanations

    described by person

    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_22/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
     durante
    -1.09
    ที่จะ
    -1.03
    Nationalité
    -0.96
    anything
    -0.96
    yden
    -0.95
    了不少
    -0.95
    already
    -0.94
     third
    -0.93
     Eğer
    -0.91
     anything
    -0.90
    POSITIVE LOGITS
     in
    1.36
    简约
    1.05
     by
    1.01
     tenere
    1.00
     hiciera
    0.98
     with
    0.98
     on
    0.96
    أن
    0.95
    𝑙
    0.95
    變得
    0.94
    Activations Density 0.028%

    No Known Activations