© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 18373
    Prev
    Next
    INDEX
    Explanations

    Valentine's Day, St. Patrick's Day

    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
    Этот
    0.68
    5
    0.66
    is
    0.65
    6
    0.64
    8
    0.61
    v
    0.59
    4
    0.59
    9
    0.59
    em
    0.57
    3
    0.57
    POSITIVE LOGITS
     Valentines
    0.83
     Valentine
    0.80
     valentine
    0.73
     valentines
    0.71
     वैलेंटाइन
    0.68
     WrestleMania
    0.64
     ചെറിയ
    0.63
     FEC
    0.63
     Ró
    0.62
     FHWA
    0.61
    Activations Density 0.005%

    No Known Activations