© 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. 2351
    Prev
    Next
    INDEX
    Explanations

    conjunctions follow punctuation

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

    comma followed by if

    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
    (),
    0.61
     ،
    0.59
     laquelle
    0.59
     lequel
    0.57
     ,
    0.57
    ซึ่ง
    0.56
    且
    0.56
    、
    0.55
     、
    0.55
     ซึ่ง
    0.54
    POSITIVE LOGITS
     since
    0.80
     despite
    0.78
     although
    0.76
     if
    0.72
     meskipun
    0.70
     चूंकि
    0.67
     because
    0.65
     mivel
    0.64
     when
    0.63
     meski
    0.63
    Activations Density 0.477%

    No Known Activations