© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9329
    Prev
    Next
    INDEX
    Explanations

    phases and projects

    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
    娇
    0.65
    从小
    0.62
    欤
    0.61
    传播
    0.61
     Arzt
    0.61
     Hacker
    0.61
    饰
    0.60
    袅
    0.59
    纹
    0.59
     صحیح
    0.57
    POSITIVE LOGITS
    projects
    0.88
     project
    0.86
     projects
    0.85
     proyecto
    0.84
    planned
    0.83
     planned
    0.82
     проекты
    0.81
     investment
    0.81
    capacity
    0.80
     projets
    0.80
    Activations Density 0.053%

    No Known Activations