© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20306
    Prev
    Next
    INDEX
    Explanations

    time units and date calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     هی
    0.55
    琇
    0.52
    螯
    0.49
    仪表
    0.48
    电压
    0.47
    碱
    0.47
    散热
    0.47
    泷
    0.46
     vutto
    0.45
     szö
    0.45
    POSITIVE LOGITS
     days
    0.98
    days
    0.88
     weeks
    0.87
    daily
    0.86
     months
    0.86
     calendar
    0.84
    month
    0.83
     month
    0.82
    week
    0.82
     giorni
    0.81
    Activations Density 0.194%

    No Known Activations