© 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-262K
    7. 27783
    Prev
    Next
    INDEX
    Explanations

    energy efficiency

    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
    痣
    0.49
    姓
    0.44
     cümle
    0.43
    细胞
    0.42
     urlpatterns
    0.42
    ovaniyu
    0.42
    maktan
    0.41
    拜
    0.41
    颉
    0.41
    ⏜
    0.40
    POSITIVE LOGITS
     energy
    1.16
     Energy
    1.08
    Energy
    1.04
     에너지
    1.04
     ENERGY
    1.02
     энерго
    0.98
    energy
    0.98
     енер
    0.98
    节能
    0.97
     energía
    0.92
    Activations Density 0.055%

    No Known Activations