© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3625
    Prev
    Next
    INDEX
    Explanations

    loop conditions, math operations

    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_16k_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
     parfaite
    0.44
     regreso
    0.43
    薪
    0.43
    原來
    0.42
    Unexpected
    0.42
    Reward
    0.41
    凵
    0.40
     retreat
    0.38
     précie
    0.38
     bargaining
    0.37
    POSITIVE LOGITS
    以降
    0.44
    olov
    0.41
    审核
    0.40
     Besuch
    0.39
    高于
    0.39
    筛
    0.39
    スポーツ
    0.38
     스포츠
    0.38
     检测
    0.38
    busch
    0.38
    Activations Density 0.335%

    No Known Activations