© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1949
    Prev
    Next
    INDEX
    Explanations

    list formatting with asterisks

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

    the neuron detects document structural markers—section headings and formatting that indicate major divisions (e.g., numbered headings and bold/markdown-style headings).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     onboarding
    0.23
    🫡
    0.22
    𝙢
    0.22
     reste
    0.21
     kamen
    0.21
     NuGet
    0.21
    երի
    0.21
     synced
    0.21
    𝐦
    0.21
    ᗰ
    0.20
    POSITIVE LOGITS
     hereinafter
    0.21
     determinada
    0.21
     especial
    0.19
     inextricably
    0.19
     உலகம்
    0.19
     sogenannten
    0.18
    osts
    0.18
     рассматри
    0.18
     arrests
    0.18
    usually
    0.17
    Activations Density 2.065%

    No Known Activations