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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 45019
    Prev
    Next
    INDEX
    Explanations

    castle, relatives, Minecraft, tokenizers

    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
     可愛
    0.51
    |,
    0.51
     สอน
    0.50
     applause
    0.49
    iscus
    0.48
     sarcastic
    0.48
     情報
    0.48
     gegangen
    0.47
     acel
    0.47
     accelerate
    0.46
    POSITIVE LOGITS
    告
    0.52
    行
    0.50
     thường
    0.49
    夜
    0.48
    想
    0.47
    有
    0.47
    腻
    0.47
    入
    0.46
    靠
    0.46
    قت
    0.45
    Activations Density 0.001%

    No Known Activations