© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4835
    Prev
    Next
    INDEX
    Explanations

    greetings and requests

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

    names followed by punctuation

    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_31_width_262k_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
     Ayrshire
    0.35
    鰥
    0.34
     கொண்டார்
    0.34
     silico
    0.33
     வெளிப்புற
    0.33
    樣本
    0.33
     अल्ट्रा
    0.32
     micrograms
    0.32
     silica
    0.31
    స్తారు
    0.31
    POSITIVE LOGITS
     please
    0.62
     ơi
    0.59
    请
    0.52
    please
    0.51
     hãy
    0.50
    you
    0.48
     PLEASE
    0.48
     you
    0.47
    你能
    0.47
    你好
    0.46
    Activations Density 0.108%

    No Known Activations