© 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. 8831
    Prev
    Next
    INDEX
    Explanations

    perfect condition or example

    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
     מאוד
    2.29
    й
    2.26
    ﺭ
    1.99
     станов
    1.99
     vun
    1.97
    િ
    1.97
    ка
    1.95
    蔔
    1.91
    Wedgwood
    1.91
    ☬
    1.88
    POSITIVE LOGITS
    aan
    2.98
    нди
    2.62
    ా
    2.61
    น
    2.53
    т
    2.48
    ו
    2.34
    нды
    2.33
    اً
    2.32
    𝐞
    2.31
    يت
    2.30
    Activations Density 0.095%

    No Known Activations