© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5313
    Prev
    Next
    INDEX
    Explanations

    information for general/informational purposes

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

    metadata or boilerplate text indicating blog post entries, page ed

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    webpage boilerplate and metadata text, including post/page administrative notices, download prompts, and privacy or policy statements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    this
    0.75
     this
    0.71
     هذا
    0.64
     ടീ
    0.64
    planar
    0.63
     পাঁ
    0.62
     этом
    0.61
     этого
    0.61
     এক্ষেত্রে
    0.60
     этому
    0.59
    POSITIVE LOGITS
     belongs
    0.69
     belonged
    0.64
     thuộc
    0.57
     belong
    0.57
    属于
    0.56
    belongs
    0.55
    業
    0.55
    也不知道
    0.55
     instalment
    0.52
     particular
    0.50
    Activations Density 0.195%

    No Known Activations