© 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-262K
    7. 111206
    Prev
    Next
    INDEX
    Explanations

    describing what things are

    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
     노트
    0.43
    ມາ
    0.42
     représentent
    0.40
    Ꮝ
    0.40
     रथ
    0.40
    兘
    0.40
     шанс
    0.39
    чаем
    0.39
    কেও
    0.39
    ейчас
    0.39
    POSITIVE LOGITS
    S
    0.45
     sufficiently
    0.42
     충분
    0.42
     sur
    0.42
    EVENT
    0.40
    ুনিক
    0.40
     الطرق
    0.39
     conditions
    0.39
     undisturbed
    0.39
    スク
    0.38
    Activations Density 0.002%

    No Known Activations