© 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. 90515
    Prev
    Next
    INDEX
    Explanations

    hotel staff, spa, packages

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

    hotel reservations and services

    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
    s
    1.41
    ים
    1.02
    ی
    0.97
    ओं
    0.89
    ри
    0.85
    ς
    0.85
    ের
    0.84
    们的
    0.81
    이가
    0.81
    ों
    0.79
    POSITIVE LOGITS
     maravilloso
    0.82
    1
    0.77
    ма
    0.74
    Months
    0.69
     arabe
    0.68
     ordinaire
    0.67
     a
    0.67
    t
    0.66
    ut
    0.66
    ంబేద్కర్
    0.66
    Activations Density 0.018%

    No Known Activations