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-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 36910
    Prev
    Next
    INDEX
    Explanations

    kitchen confrontation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    да
    0.46
     the
    0.46
    ма
    0.46
    رف
    0.45
    درا
    0.43
    ق
    0.42
    meng
    0.42
    도
    0.41
    帮
    0.41
    熬
    0.41
    POSITIVE LOGITS
     různých
    0.46
     azure
    0.44
     azimuthal
    0.44
     umožňuje
    0.44
     adapter
    0.44
     จำนวน
    0.42
    蜿
    0.42
     mnoho
    0.42
     az
    0.42
     Clubs
    0.42
    Activations Density 0.001%

    No Known Activations