© 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. 2480
    Prev
    Next
    INDEX
    Explanations

    GMT followed by timezone offset

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

    number followed by plus

    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
     lymphatic
    0.43
    特定的
    0.39
     குறிப்பிட்ட
    0.39
     tertentu
    0.38
    潑
    0.38
    noopener
    0.38
     bestimmten
    0.38
     கூறிய
    0.37
     diagnóstico
    0.37
    																						
    0.37
    POSITIVE LOGITS
    +#
    0.65
    +
    0.60
    +//
    0.55
    +},
    0.54
    +{
    0.53
    +%
    0.53
    +\
    0.51
    +}
    0.49
    +|
    0.49
    +[
    0.49
    Activations Density 0.002%

    No Known Activations