© 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. 199953
    Prev
    Next
    INDEX
    Explanations

    past and present participial adjectives

    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
    สัมพันธ์
    0.48
     functional
    0.48
    傷
    0.48
     pine
    0.47
    การ
    0.46
    Pittsburgh
    0.46
    ቈ
    0.45
    left
    0.44
     \
    0.44
    🠀
    0.44
    POSITIVE LOGITS
     émer
    0.46
    电流
    0.43
     هسه
    0.43
     incidentally
    0.42
     aggrieved
    0.40
    全新的
    0.40
     Resolutions
    0.39
    比亚
    0.38
     Instal
    0.38
     Ayurvedic
    0.37
    Activations Density 0.002%

    No Known Activations