© 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. 3126
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating purpose or division

    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
    urov
    0.78
    ector
    0.73
     purchased
    0.73
    篒
    0.71
     overlaid
    0.70
     Bial
    0.70
    raded
    0.70
    erver
    0.70
    phalodes
    0.69
    ὁ
    0.68
    POSITIVE LOGITS
     menjadi
    0.78
     нельзя
    0.74
     가지
    0.73
     ফ্লাইট
    0.73
     완전
    0.73
    ใช้
    0.69
     hijau
    0.69
     become
    0.68
     रूप
    0.68
     можна
    0.68
    Activations Density 0.180%

    No Known Activations