© 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. 1709
    Prev
    Next
    INDEX
    Explanations

    formatting, offers, companies

    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
    灭
    0.42
    爆炸
    0.41
    ปรา
    0.41
     ле
    0.40
     endian
    0.40
    体积
    0.40
    Constants
    0.39
    手术
    0.39
    Length
    0.39
    บ
    0.38
    POSITIVE LOGITS
     Angebote
    0.49
     erbjuder
    0.49
     ඔබට
    0.46
     Offers
    0.46
     Companies
    0.45
     offers
    0.44
     bedrijven
    0.43
     Banking
    0.43
     companies
    0.43
     ofrece
    0.42
    Activations Density 0.037%

    No Known Activations