© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3065
    Prev
    Next
    INDEX
    Explanations

    advertising, sponsorships, affiliate marketing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     Limestone
    0.71
     Stone
    0.69
     stone
    0.67
     புல
    0.66
     গিয়
    0.65
    ভীর
    0.65
    输入的
    0.64
    釜
    0.64
     Prescott
    0.64
     मुहूर्त
    0.64
    POSITIVE LOGITS
     Affiliate
    1.23
     affiliate
    1.22
     Advertising
    1.21
     Sponsorship
    1.21
     sponsorships
    1.19
     Ads
    1.17
     advertisement
    1.15
     sponsorship
    1.14
    Advertising
    1.13
     ads
    1.13
    Activations Density 0.184%

    No Known Activations