© 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. 13756
    Prev
    Next
    INDEX
    Explanations

    fill in the blank

    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
    c
    0.66
    et
    0.52
    onu
    0.52
    رسی
    0.51
     आक्रमण
    0.50
    ರಳ
    0.49
    b
    0.49
     axe
    0.49
     உட்பட
    0.48
    绪
    0.48
    POSITIVE LOGITS
     filling
    1.54
     Fill
    1.52
    Filling
    1.51
    Fill
    1.48
     Filling
    1.48
     fill
    1.45
     fills
    1.42
     запол
    1.40
    filling
    1.38
    fill
    1.33
    Activations Density 0.054%

    No Known Activations