© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13613
    Prev
    Next
    INDEX
    Explanations

    words ending in ies

    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_65k_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
     BlueprintName
    0.40
    )>=
    0.39
    ন্ত্রণ
    0.39
     undertaken
    0.39
     analysed
    0.39
     eius
    0.38
    是由
    0.38
     LANGUAGE
    0.37
    ➛
    0.37
     PERSONNEL
    0.37
    POSITIVE LOGITS
     juntos
    0.68
    他们在
    0.59
    共同
    0.57
    They
    0.56
     They
    0.55
     loro
    0.54
     họ
    0.54
    他們
    0.53
     তাঁদের
    0.52
     njima
    0.52
    Activations Density 0.145%

    No Known Activations