© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4232
    Prev
    Next
    INDEX
    Explanations

    regularly

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

    regular intervals

    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
    ⏟
    0.36
    firmasi
    0.35
    ष्‍ट
    0.33
    សម្រ
    0.33
    త్ర
    0.33
    annotations
    0.32
    aundry
    0.32
    millimeters
    0.31
    ᙱ
    0.31
    ArgsConstructor
    0.31
    POSITIVE LOGITS
     regularly
    4.03
     регуляр
    4.03
     regular
    3.98
     регулярно
    3.94
    regular
    3.88
     Regularly
    3.80
    Regular
    3.77
    定期
    3.75
     नियमित
    3.72
     pravidel
    3.66
    Activations Density 0.650%

    No Known Activations