© 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. 11915
    Prev
    Next
    INDEX
    Explanations

    not knowing why

    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
     a
    -2.16
     behalf
    -1.73
    䉴
    -1.63
    इटम
    -1.63
    푢
    -1.48
    かもし
    -1.45
    了不少
    -1.45
     the
    -1.45
     to
    -1.44
     несмотря
    -1.41
    POSITIVE LOGITS
    ΕΣ
    1.69
    🌟
    1.60
    หรือ
    1.52
    Like
    1.45
    💁
    1.45
    Can
    1.44
    😆
    1.43
    🌻
    1.41
    และ
    1.40
    🎄
    1.36
    Activations Density 0.009%

    No Known Activations