© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2559
    Prev
    Next
    INDEX
    Explanations

    measurements and conversions

    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_13_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
     negli
    1.01
     exig
    1.01
     trong
    0.95
     sebagai
    0.95
    ne
    0.95
     exige
    0.94
     dalam
    0.93
    В
    0.93
     pentru
    0.91
     requiere
    0.91
    POSITIVE LOGITS
     攵
    1.46
     然后
    1.34
     ৃ
    1.30
     Iyer
    1.29
     プリント
    1.28
     "*****
    1.27
    FromThe
    1.26
    ,\,\,\,\
    1.26
     遊ん
    1.23
     Θε
    1.23
    Activations Density 0.021%

    No Known Activations