© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2499
    Prev
    Next
    INDEX
    Explanations

    months associated with volumes

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

    months and dates

    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
    近年
    0.48
    近年来
    0.45
    いに
    0.44
     হইয়াছে
    0.43
    isNaN
    0.40
    ⊆
    0.39
    DebugType
    0.38
    ABCDEFGHIJKLMNOP
    0.38
    Գ
    0.38
    Liên
    0.37
    POSITIVE LOGITS
     November
    3.41
     October
    3.39
     February
    3.39
     September
    3.38
     April
    3.34
     December
    3.25
     June
    3.23
     January
    3.16
     July
    3.13
     August
    2.97
    Activations Density 1.219%

    No Known Activations