© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 48344
    Prev
    Next
    INDEX
    Explanations

    Narita airport arrival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    larının
    1.01
    м
    0.88
    lıkla
    0.87
    ম
    0.81
    larını
    0.80
    larla
    0.77
    )
    0.76
     separa
    0.75
     traiter
    0.74
    l
    0.73
    POSITIVE LOGITS
    2
    0.99
    د
    0.77
    ش
    0.76
    O
    0.72
    دين
    0.70
    Clinic
    0.70
    Dish
    0.69
    دخل
    0.68
    Effect
    0.67
    Button
    0.66
    Activations Density 0.001%

    No Known Activations