© 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-65K
    7. 48386
    Prev
    Next
    INDEX
    Explanations

    connecting, appearing, simply, breeze, mere, soil, research, exhausting, panic

    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
    কর্ণ
    0.48
    基本上
    0.45
    FDMA
    0.45
    cephal
    0.43
    শিক্ষ
    0.43
     &.
    0.43
     えっと
    0.42
     esattamente
    0.42
    underwear
    0.41
    different
    0.41
    POSITIVE LOGITS
     emit
    0.42
    亲自
    0.42
     দেন
    0.41
    방송
    0.41
    லாத
    0.39
    逊
    0.39
     resent
    0.38
     对
    0.38
     lifeless
    0.38
     chez
    0.38
    Activations Density 0.001%

    No Known Activations