© 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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 336
    Prev
    Next
    INDEX
    Explanations

    computer, followed by items

    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_16k_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
     борьбы
    1.38
    𝗮
    1.37
    𝗸
    1.34
    𝘂
    1.26
    𝘇
    1.23
    𝗱
    1.21
    о
    1.21
    𝖺
    1.20
     encouraging
    1.19
     fact
    1.19
    POSITIVE LOGITS
    ยนต์
    1.97
    ن
    1.60
    ン
    1.32
    ه
    1.30
    مح
    1.16
    valueChanged
    1.12
    એસ
    1.11
    j
    1.11
    পত্রে
    1.11
    страи
    1.10
    Activations Density 0.868%

    No Known Activations