© 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. 2495
    Prev
    Next
    INDEX
    Explanations

    whether... that

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

    while that

    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
    Esta
    0.59
     ইহাদের
    0.59
     ovom
    0.57
     significantly
    0.47
     Esta
    0.47
     	i
    0.47
     وهذه
    0.46
    このような
    0.44
     ovoj
    0.43
    此类
    0.42
    POSITIVE LOGITS
     đó
    3.25
    That
    3.14
     THAT
    3.13
     That
    3.03
     ذلك
    2.98
    那
    2.77
    THAT
    2.72
     того
    2.67
    นั้น
    2.66
    那是
    2.61
    Activations Density 1.991%

    No Known Activations