© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1803
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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_13_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
    倍
    0.93
     മഹ
    0.92
    著名的
    0.86
    World
    0.85
     vardır
    0.83
     CBL
    0.82
     Vascular
    0.82
     বিখ্যাত
    0.82
     컴
    0.80
     좋은
    0.80
    POSITIVE LOGITS
     gaps
    0.59
     gap
    0.58
    ुन
    0.58
     slightly
    0.53
     completely
    0.52
     misalignment
    0.52
     loss
    0.51
     remotely
    0.50
     casi
    0.50
     dissent
    0.49
    Activations Density 0.489%

    No Known Activations