© 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. 191533
    Prev
    Next
    INDEX
    Explanations

    gourmet ingredients and dishes

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

    with honey or salmon

    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
     блю
    0.51
     люби
    0.47
     çeşit
    0.47
    🥫
    0.47
    맛
    0.46
    🥤
    0.45
     разнови
    0.44
     चिकन
    0.44
     hamburgers
    0.44
     yummy
    0.43
    POSITIVE LOGITS
     presentada
    0.51
    プレゼ
    0.48
    QE
    0.46
    化粧
    0.45
    кон
    0.42
     presenting
    0.42
    繭
    0.41
    Guests
    0.41
     guests
    0.41
     presentó
    0.41
    Activations Density 0.146%

    No Known Activations