© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3580
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    시
    0.65
     Men
    0.60
    ella
    0.59
    ולם
    0.59
    ಿಯಾ
    0.59
     men
    0.58
     مرد
    0.58
     нару
    0.57
    暴力
    0.56
     poorly
    0.56
    POSITIVE LOGITS
     puisqu
    0.94
     puisque
    0.91
     بالنسبة
    0.82
    🤖
    0.82
    বিদ্যাল
    0.82
     amusing
    0.81
     inasmuch
    0.80
     بالنسبه
    0.80
     ಸಾಧ
    0.79
     Nowadays
    0.79
    Activations Density 0.207%

    No Known Activations