© 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-65K
    4. 49529
    Prev
    Next
    INDEX
    Explanations

    timeframe, evolution, and discussion topics

    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
    ="(
    0.44
    ela
    0.42
    ible
    0.41
    able
    0.41
    願意
    0.41
    autre
    0.41
    enger
    0.40
    iture
    0.40
    เพราะ
    0.39
    漪
    0.38
    POSITIVE LOGITS
     Fark
    0.47
    쓰
    0.46
     Yath
    0.43
    同期
    0.42
     Maver
    0.42
     Aralık
    0.40
    ívá
    0.40
    叠加
    0.40
     Tiktok
    0.39
    同样的
    0.39
    Activations Density 0.003%

    No Known Activations