© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14549
    Prev
    Next
    INDEX
    Explanations

    fuel metabolism for energy

    np_acts-logits-general · gemini-2.5-flash-lite

    glucose metabolism and respiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    宪
    0.76
    悛
    0.72
     دید
    0.70
    选举
    0.68
     वीरता
    0.68
     امنیت
    0.68
    谍
    0.66
    行业的
    0.66
    燹
    0.65
    飞机
    0.63
    POSITIVE LOGITS
     metabolic
    1.29
     mitochond
    1.22
     metabol
    1.19
     glucose
    1.19
     metabolism
    1.18
     metabolized
    1.15
     mitochondria
    1.14
     pyruvate
    1.13
    代謝
    1.10
     carbohydrate
    1.09
    Activations Density 0.040%

    No Known Activations