© 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
    3. 53-GEMMASCOPE-2-RES-65K
    4. 8556
    Prev
    Next
    INDEX
    Explanations

    legal and arts contexts

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

    stress response hormones

    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_53_width_65k_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
     ٹ
    0.50
    ২৯
    0.47
    กัด
    0.46
     ২৬
    0.44
     jQuery
    0.44
     যন্ত্রপাতি
    0.44
    餃
    0.44
    ২৬
    0.44
    ня
    0.43
     ৬
    0.43
    POSITIVE LOGITS
    водитель
    0.43
     insinu
    0.41
     Commonly
    0.39
     sofern
    0.39
    7
    0.39
    ꯁ
    0.37
     earnestly
    0.37
     vehement
    0.37
     equil
    0.37
     shí
    0.37
    Activations Density 0.326%

    No Known Activations