© 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. 108343
    Prev
    Next
    INDEX
    Explanations

    AI stress testing

    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
     participation
    0.43
     mempunyai
    0.43
     participar
    0.43
     zna
    0.41
    ඍ
    0.41
    তাহাদের
    0.41
     hath
    0.40
    жуть
    0.40
     ഒന്നും
    0.40
    امل
    0.40
    POSITIVE LOGITS
    表示
    0.53
     để
    0.48
    预测
    0.47
    让
    0.46
     对于
    0.44
     Regex
    0.43
    Để
    0.43
    堆
    0.43
     untuk
    0.43
     表示
    0.43
    Activations Density 0.007%

    No Known Activations