© 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. 2684
    Prev
    Next
    INDEX
    Explanations

    small size or amount

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

    small amounts, tasks, personal

    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
    大型
    0.57
     বিশাল
    0.51
     enormes
    0.49
     عظیم
    0.46
     large
    0.46
     lớn
    0.45
    槊
    0.45
     крупные
    0.44
     huge
    0.43
     largas
    0.43
    POSITIVE LOGITS
     $(<
    1.34
     (<
    1.23
    pox
    1.09
     (\<
    1.04
    (<
    0.98
    🤏
    0.97
     insignificant
    0.97
    ish
    0.93
    小的
    0.79
    sized
    0.75
    Activations Density 0.259%

    No Known Activations