© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 183321
    Prev
    Next
    INDEX
    Explanations

    Los Angeles International Airport

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

    recipes, dye, desert

    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
    Mack
    0.50
     প্রথমেই
    0.46
    핳
    0.45
     Mack
    0.45
     정의역
    0.44
    ల్
    0.43
    ELLOW
    0.43
    etek
    0.43
    겉
    0.42
    멩
    0.42
    POSITIVE LOGITS
     hiện
    0.42
     Desert
    0.42
     nghiệp
    0.40
    डले
    0.40
    شاركة
    0.40
     actuelle
    0.40
     condizione
    0.40
     آتی
    0.40
     dessert
    0.40
     preventiva
    0.40
    Activations Density 0.001%

    No Known Activations