Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 292
    Prev
    Next
    INDEX
    Explanations

    tools and programs

    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_16_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
     régler
    0.56
     sensibilité
    0.55
    ları
    0.55
    wach
    0.54
    aları
    0.52
    葶
    0.52
     найти
    0.51
     ด้าน
    0.51
    几天
    0.51
    威胁
    0.51
    POSITIVE LOGITS
    Tw
    0.54
    quan
    0.51
    ם
    0.49
    qu
    0.49
    f
    0.48
    It
    0.48
    Ts
    0.47
    Inicial
    0.47
    0
    0.47
    Financial
    0.46
    Activations Density 0.000%

    No Known Activations