© 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. 17380
    Prev
    Next
    INDEX
    Explanations

    passage of time

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

    time passed or elapsed

    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
     landings
    0.39
    </footer>
    0.38
     stair
    0.38
     அளவுக்கு
    0.36
     চূড়ান্ত
    0.36
     stairway
    0.35
    شنبه
    0.35
    pinned
    0.35
     Polymers
    0.35
     ৃ
    0.34
    POSITIVE LOGITS
     elapsed
    1.86
     elapse
    1.73
     passing
    1.64
    elapsed
    1.64
     बीत
    1.63
     lapse
    1.55
     lapsed
    1.53
     passed
    1.52
    Elapsed
    1.49
    passing
    1.48
    Activations Density 0.033%

    No Known Activations