© 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. 17-GEMMASCOPE-2-RES-16K
    4. 8213
    Prev
    Next
    INDEX
    Explanations

    type VARCHAR, type of, type:

    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
     terapé
    2.90
     sàng
    2.79
    ای
    2.61
    ر
    2.49
     افز
    2.47
    辔
    2.45
     pertain
    2.41
    boosting
    2.39
    ے
    2.36
     unitarity
    2.36
    POSITIVE LOGITS
    ت
    3.60
    𝚐
    2.58
    ying
    2.40
    鸯
    2.40
    𝑦
    2.34
    UseDebug
    2.32
     contingent
    2.25
    ve
    2.24
     bỏ
    2.18
    וף
    2.17
    Activations Density 0.250%

    No Known Activations