© 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. 3750
    Prev
    Next
    INDEX
    Explanations

    companies and financial information

    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
     интел
    0.59
    素质
    0.57
    颢
    0.57
    Causes
    0.56
    损伤
    0.55
     苏
    0.54
    霭
    0.54
    逻
    0.53
    欤
    0.53
    闿
    0.51
    POSITIVE LOGITS
     holdings
    0.73
     subsidiaries
    0.71
     financials
    0.71
     shareholders
    0.68
     investor
    0.68
     shares
    0.66
     shareholder
    0.66
     investors
    0.65
     financ
    0.64
     financing
    0.63
    Activations Density 0.072%

    No Known Activations