© 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. 2588
    Prev
    Next
    INDEX
    Explanations

    decades and historical periods

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

    decades and years

    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
     মিনিটে
    0.42
     আসন্ন
    0.42
     sebanyak
    0.41
     Monat
    0.39
    OCITY
    0.38
     सामान्य
    0.38
    Datum
    0.38
    岦
    0.38
     ক্রিকেট
    0.37
     Normally
    0.37
    POSITIVE LOGITS
     seventies
    2.38
     fifties
    2.36
     sixties
    2.30
     eighties
    2.28
     nineties
    2.19
     thirties
    2.17
     twenties
    2.03
     mid
    1.84
     late
    1.79
     twentieth
    1.68
    Activations Density 0.386%

    No Known Activations