© 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. 28618
    Prev
    Next
    INDEX
    Explanations

    Simpsons, Caesar, Springfield

    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
    ה
    1.01
    ه
    0.99
    d
    0.92
    a
    0.89
    د
    0.88
    সম্প
    0.77
    ‌اند
    0.76
    ات
    0.72
    י
    0.72
    ب
    0.71
    POSITIVE LOGITS
    com
    0.80
    ana
    0.78
    ことです
    0.77
    ために
    0.75
    ov
    0.75
     sosok
    0.74
     DOI
    0.73
    in
    0.73
    irteen
    0.73
    СО
    0.73
    Activations Density 0.003%

    No Known Activations