© 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. 17591
    Prev
    Next
    INDEX
    Explanations

    durations of years or days

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

    durations in days, years, or minutes

    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
     millilit
    0.49
     سینٹی
    0.45
     kilograms
    0.43
     kilow
    0.43
    摄
    0.43
     கிலோ
    0.41
     minutes
    0.41
     मीटर
    0.40
     किलो
    0.40
    millimeters
    0.38
    POSITIVE LOGITS
     روزہ
    0.61
     दिवसीय
    0.59
    }$-
    0.51
     yıllık
    0.49
     वर्षीय
    0.48
    års
    0.48
    yr
    0.47
    際の
    0.46
    jährige
    0.45
    ramble
    0.44
    Activations Density 0.076%

    No Known Activations