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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10852
    Prev
    Next
    INDEX
    Explanations

    avoidance or prevention

    np_acts-logits-general · gemini-2.5-flash-lite

    phenomena occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Combine
    0.48
    全体
    0.47
    Combine
    0.45
    彦
    0.43
    唯一
    0.41
    部长
    0.41
    UPI
    0.41
    広い
    0.41
    中文
    0.40
     Hatch
    0.40
    POSITIVE LOGITS
     ocurrió
    0.64
     terjadi
    0.62
    频繁
    0.60
    发生在
    0.60
     സംഭവ
    0.58
     발생
    0.56
    擾
    0.56
     occurred
    0.55
    不安定
    0.55
     ciddi
    0.55
    Activations Density 0.057%

    No Known Activations