© 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. 17-GEMMASCOPE-2-RES-16K
    7. 10534
    Prev
    Next
    INDEX
    Explanations

    write sentences or paragraphs

    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_17_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
     raro
    1.12
    lder
    1.12
    𝗲
    1.10
    વાર
    1.09
    𝗘
    1.08
     karşınız
    1.08
     PWR
    1.04
     важ
    1.03
    ▇
    1.02
    大変
    1.01
    POSITIVE LOGITS
    ين
    1.52
     siguientes
    1.26
    야
    1.25
    reni
    1.17
     만들기
    1.13
    ።
    1.12
    warming
    1.12
     Сле
    1.10
     हाइड्रो
    1.09
     Initialize
    1.08
    Activations Density 0.101%

    No Known Activations