© 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-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 587
    Prev
    Next
    INDEX
    Explanations

    text HOME to 741741

    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_22_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
    층
    0.93
     THREE
    0.93
     thre
    0.85
    三个
    0.84
     дву
    0.82
     three
    0.79
     ત્રણ
    0.79
     üç
    0.76
     thirds
    0.75
     '|
    0.75
    POSITIVE LOGITS
     ২০১৯
    1.57
     ২০১৮
    1.51
    ২০
    1.48
     ২০১০
    1.46
     ২০১৭
    1.46
     ২০১৬
    1.45
     ২০২১
    1.45
     २०१
    1.44
    平成
    1.40
     ২০১৫
    1.38
    Activations Density 0.789%

    No Known Activations