© 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. 80001
    Prev
    Next
    INDEX
    Explanations

    data subject for

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

    foreign language words

    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
    ues
    0.50
    uce
    0.50
    nhof
    0.49
    es
    0.49
    elope
    0.49
    uidas
    0.48
    ức
    0.47
    //{
    0.46
    apart
    0.46
    ={
    0.46
    POSITIVE LOGITS
    стрі
    0.45
     ensimmä
    0.43
    ルート
    0.42
     sitten
    0.42
    まだ
    0.41
     মুহাম্ম
    0.41
    明年
    0.40
    もあった
    0.40
    сія
    0.40
    運輸
    0.39
    Activations Density 0.000%

    No Known Activations