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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2733
    Prev
    Next
    INDEX
    Explanations

    "I" statements

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

    I say

    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
     bize
    0.73
    给我们
    0.73
     bizi
    0.66
     ourselves
    0.61
     pihaknya
    0.59
    让我们
    0.56
    讓我們
    0.55
    помним
    0.54
     nám
    0.52
     nuest
    0.51
    POSITIVE LOGITS
     আমি
    3.30
     मैंने
    3.17
     tôi
    3.13
    私は
    3.09
     मैं
    3.08
     ನಾನು
    2.98
     నేను
    2.98
     நான்
    2.95
     ഞാൻ
    2.95
     저는
    2.88
    Activations Density 3.168%

    No Known Activations