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. 7852
    Prev
    Next
    INDEX
    Explanations

    numbered lists and percentages

    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
    dimethyl
    2.03
    panelMenuList
    2.03
     Hälfte
    2.03
    lerin
    1.98
     Nuestra
    1.97
    quinoxaline
    1.96
    S
    1.91
    Marathi
    1.90
    <table>
    1.89
    要
    1.88
    POSITIVE LOGITS
    st
    2.74
    ️⃣
    2.28
    he
    2.22
    การ
    2.16
    ′
    2.15
    ″
    2.10
    স
    2.09
    ल
    2.08
    на
    2.01
    ⁄
    1.96
    Activations Density 0.255%

    No Known Activations