© 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. 4913
    Prev
    Next
    INDEX
    Explanations

    mathematical identities and relationships involving binomial coefficients.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    numbers after "e"

    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
    监狱
    0.55
    देशीर
    0.54
    财政
    0.54
    欧盟
    0.53
    资本
    0.52
     veřej
    0.52
    Governance
    0.52
    黢
    0.52
    EnglishMarks
    0.52
    检察
    0.52
    POSITIVE LOGITS
     x
    0.70
    0
    0.69
     A
    0.68
     u
    0.67
     C
    0.61
    x
    0.61
     first
    0.59
    p
    0.59
     {
    0.58
     v
    0.57
    Activations Density 0.176%

    No Known Activations