© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 32426
    Prev
    Next
    INDEX
    Explanations

    code structure and foreign texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     strate
    0.39
    ગ
    0.38
     ্
    0.38
     GLE
    0.37
    Paradise
    0.37
     shel
    0.37
    つ
    0.36
    तन
    0.36
    ッコ
    0.36
    gün
    0.36
    POSITIVE LOGITS
    "=>
    0.41
    ార్క్
    0.41
     erklärt
    0.38
     ஆகும்
    0.37
    waitForIdleSync
    0.37
    讲
    0.37
     بسيط
    0.37
    setClass
    0.37
    綘
    0.36
     সার্ভ
    0.35
    Activations Density 0.000%

    No Known Activations