© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9342
    Prev
    Next
    INDEX
    Explanations

    AI is not a professional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     Crafted
    1.05
     rabbis
    0.90
     executives
    0.89
     bullies
    0.86
    ViewById
    0.85
    ⎮
    0.85
     patriarch
    0.82
     cropped
    0.82
     crafted
    0.81
    ⎆
    0.80
    POSITIVE LOGITS
    요
    0.90
    ুর
    0.86
     આવ્યો
    0.77
    지를
    0.77
     будем
    0.76
     ちゃん
    0.74
    ется
    0.73
     ulterior
    0.72
    し
    0.70
    organization
    0.70
    Activations Density 0.050%

    No Known Activations