© 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. 15644
    Prev
    Next
    INDEX
    Explanations

    infrastructure projects and development

    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
    饮食
    0.71
    流畅
    0.70
    焦虑
    0.70
     儿童
    0.69
    培养
    0.69
    神经
    0.68
    娇
    0.68
    阏
    0.68
     Verständnis
    0.67
    细胞
    0.66
    POSITIVE LOGITS
    projects
    1.28
     projects
    1.20
    construction
    1.20
     project
    1.16
     proyecto
    1.16
    PROJECT
    1.15
     infrastructure
    1.14
    プロジェクト
    1.14
     construction
    1.13
    project
    1.13
    Activations Density 0.048%

    No Known Activations