© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 118946
    Prev
    Next
    INDEX
    Explanations

    schema, urls, advice, whether

    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
     e
    0.59
     waveforms
    0.52
     authentication
    0.49
     ..
    0.47
     audible
    0.47
     Waterfall
    0.46
     Service
    0.45
    োলন
    0.45
    orean
    0.45
     renovation
    0.44
    POSITIVE LOGITS
    ᱕
    0.62
     прем
    0.52
    ក្រោម
    0.50
     இறு
    0.50
     росли
    0.50
     наступ
    0.49
    n
    0.48
     racconto
    0.48
    drá
    0.47
    anı
    0.46
    Activations Density 0.000%

    No Known Activations