© 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. 2678
    Prev
    Next
    INDEX
    Explanations

    indonesia, jakarta, jalan

    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
     설계
    1.22
     급
    1.18
    意大利
    1.15
    의
    1.14
     사
    1.14
    铜
    1.13
    하는
    1.12
    에
    1.12
     및
    1.10
     보
    1.09
    POSITIVE LOGITS
     Indonesia
    2.50
     Indonesian
    2.41
     Jakarta
    2.21
     Bahasa
    2.19
     tidak
    2.17
     hanya
    2.17
     juga
    2.13
     Indones
    2.11
     sudah
    2.08
     Rumah
    2.08
    Activations Density 0.055%

    No Known Activations