© 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. 5453
    Prev
    Next
    INDEX
    Explanations

    social media questions recommendations

    np_acts-logits-general · gemini-2.5-flash-lite

    user instructions that directly address the assistant in second person (you/your), including imperatives, role assignments, and requests.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     அல்லது
    0.51
    あるいは
    0.45
    ஃப
    0.44
    或其他
    0.44
     কিংবা
    0.43
    または
    0.43
    สำหรับ
    0.43
    难以
    0.43
    ၊
    0.43
     bzw
    0.42
    POSITIVE LOGITS
    0.59
     also
    0.52
     counc
    0.45
     tshirt
    0.44
     tiktok
    0.43
     marie
    0.43
     wont
    0.43
     instagram
    0.43
     now
    0.43
     whatsapp
    0.42
    Activations Density 0.567%

    No Known Activations