Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7319
    Prev
    Next
    INDEX
    Explanations

    function returns void

    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_262k_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
    isHidden
    1.48
    owej
    1.45
    ными
    1.40
    এছ
    1.40
     bon
    1.37
    ſe
    1.36
    ным
    1.36
    ো
    1.32
    lső
    1.32
    َان
    1.32
    POSITIVE LOGITS
     Untersuchung
    1.90
    内容
    1.70
    小说
    1.70
    ज
    1.69
    ึ่ง
    1.61
     isom
    1.58
    Ṕ
    1.55
    数据
    1.54
    ریح
    1.54
    चित्र
    1.52
    Activations Density 0.024%

    No Known Activations