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

    code block closing

    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_9_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
    ية
    0.82
     legally
    0.76
     қара
    0.76
    奭
    0.75
    <bos>
    0.75
    ్‌
    0.74
    =\
    0.73
    ^{*}
    0.73
    ed
    0.73
    ism
    0.73
    POSITIVE LOGITS
    sers
    1.05
    تی
    1.00
    tener
    0.97
    tir
    0.94
    其他
    0.93
    ties
    0.92
     Gerade
    0.89
    tran
    0.89
    tble
    0.88
     में
    0.86
    Activations Density 1.535%

    No Known Activations