© 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-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2038
    Prev
    Next
    INDEX
    Explanations

    reaction followed by between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_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
    ῦ
    0.83
    imetre
    0.82
    olat
    0.80
    amata
    0.80
     केलेली
    0.78
    onate
    0.78
    associated
    0.77
    匹
    0.77
    相关
    0.76
    ếng
    0.75
    POSITIVE LOGITS
     between
    4.65
    between
    4.29
     между
    4.21
     Between
    4.13
     BETWEEN
    4.07
     zwischen
    3.96
     giữa
    3.92
     entre
    3.83
     mellan
    3.82
    Between
    3.81
    Activations Density 0.848%

    No Known Activations