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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7460
    Prev
    Next
    INDEX
    Explanations

    programming keywords and methods

    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
    地铁
    1.37
    ل
    1.35
    𝑻
    1.34
    ​​
    1.33
    𝘱
    1.33
     Melissa
    1.32
     жесто
    1.32
    <0xF3>
    1.29
    𝑇
    1.29
    splitted
    1.29
    POSITIVE LOGITS
    ień
    1.21
     यावेळी
    1.14
     लिए
    1.12
    áty
    1.07
    ắn
    1.07
    াবি
    1.06
     respectiv
    1.05
    ئے
    1.04
     আও
    1.03
    íme
    1.02
    Activations Density 0.278%

    No Known Activations