© 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-65K
    7. 4727
    Prev
    Next
    INDEX
    Explanations

    So, yes

    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
     cok
    0.48
    م
    0.48
     sone
    0.46
     radius
    0.45
    \
    0.45
    벤트
    0.42
     congestion
    0.42
     agendas
    0.42
    ی
    0.42
    सुक
    0.41
    POSITIVE LOGITS
     ঠান্ডা
    0.48
     முன்ப
    0.47
     রঙিন
    0.46
    赧
    0.46
     multifaceted
    0.46
     ব্যাকটেরিয়া
    0.45
     allgemein
    0.45
     মূলত
    0.45
    windowFixedWidth
    0.45
     aufgel
    0.45
    Activations Density 0.005%

    No Known Activations