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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 21891
    Prev
    Next
    INDEX
    Explanations

    explaining concepts, figures, and functions

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

    This neuron detects the start of fenced code blocks (triple-backtick ``` code delimiters) in the text.

    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
    zenes
    0.43
     পরিদর্শন
    0.43
    沬
    0.43
    昦
    0.42
    ष्मा
    0.41
     sig
    0.41
     greenish
    0.41
    perror
    0.41
    ifies
    0.40
    azón
    0.40
    POSITIVE LOGITS
    ">
    0.48
    ク
    0.48
    <b>
    0.47
    Ryan
    0.45
    <strong>
    0.45
    خل
    0.45
     Avec
    0.44
    Reusable
    0.42
    Not
    0.42
    まさに
    0.42
    Activations Density 0.560%

    No Known Activations