© 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. 28768
    Prev
    Next
    INDEX
    Explanations

    hotels, inns, rooms, resorts

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

    ecommerce website

    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
    廚
    0.44
    ಡುಗೆ
    0.44
     кухня
    0.41
     রান্না
    0.40
    キッチン
    0.40
    রার
    0.40
     забезпе
    0.39
    setcounter
    0.38
    離開
    0.38
     кух
    0.38
    POSITIVE LOGITS
     적
    0.49
     Pank
    0.42
     Inn
    0.40
     ප්‍ර
    0.40
     incurable
    0.40
     Desai
    0.40
    opan
    0.39
     अनुमोदन
    0.39
     apro
    0.39
     motel
    0.39
    Activations Density 0.000%

    No Known Activations