© 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. 1565
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    years, percentages, currencies, units

    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
    ர்ஸ்
    0.44
    窍
    0.39
    Majority
    0.38
    ्हान
    0.37
    ঙ্কের
    0.36
     हमे
    0.36
     প্রক্রিয়া
    0.36
    тельством
    0.36
     প্রক্রিয়া
    0.33
     Specifically
    0.33
    POSITIVE LOGITS
    0
    0.64
    년대
    0.54
    %
    0.51
    fficial
    0.46
    3
    0.43
    ~
    0.41
    9
    0.40
    8
    0.39
    ″
    0.39
    2
    0.39
    Activations Density 0.335%

    No Known Activations