© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21192
    Prev
    Next
    INDEX
    Explanations

    data analysis and programming

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

    This neuron activates on content-bearing keywords and topic-heading tokens that mark important concepts or emphasis 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
     பகுதிக
    0.50
     mniej
    0.46
     рр
    0.45
    汥
    0.44
     റോ
    0.43
    أي
    0.42
     वर्गों
    0.42
    ounters
    0.42
    োপাধ
    0.42
     liberd
    0.42
    POSITIVE LOGITS
    ネス
    0.46
    s
    0.45
    ↵
    0.45
     Dangerous
    0.42
    cs
    0.39
    ban
    0.37
     strategic
    0.37
    রত
    0.37
     Ivory
    0.37
    he
    0.36
    Activations Density 0.267%

    No Known Activations