© 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. 10-GEMMASCOPE-RES-131K
    7. 90342
    Prev
    Next
    INDEX
    Explanations

    declarations and statements

    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
    玙
    -2.52
     для
    -2.42
     馆
    -2.39
    ativement
    -2.38
    ৢ
    -2.20
     -
    -2.20
    纐
    -2.19
     برای
    -2.14
     In
    -2.06
     für
    -2.06
    POSITIVE LOGITS
    0
    3.31
    ”:
    2.48
    “
    2.34
    ”)
    2.31
     that
    2.31
     車場
    2.28
    1
    2.28
    ”
    2.25
    ”;
    2.23
    :”
    2.16
    Activations Density 0.013%

    No Known Activations