© 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-262K
    7. 8316
    Prev
    Next
    INDEX
    Explanations

    access and answers

    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
    ی
    2.05
    ು
    1.94
    y
    1.87
    י
    1.85
    ுங்கள்
    1.62
    𝘆
    1.58
    yse
    1.55
     سازی
    1.52
    ν
    1.51
    ல்லை
    1.50
    POSITIVE LOGITS
    ون
    1.71
    दायक
    1.42
     cómod
    1.39
     koń
    1.36
    𝒇
    1.33
     morphism
    1.32
    য়ান
    1.32
    শস্ত্র
    1.30
    ک
    1.29
     conocido
    1.28
    Activations Density 0.222%

    No Known Activations