© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36003
    Prev
    Next
    INDEX
    Explanations

    conditions or requirements

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

    The neuron fires on words expressing requirement or dependency—i.e. terms that signal something is needed or contingent.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     when
    -1.15
    瀟
    -1.06
    cshtml
    -0.88
    secara
    -0.86
    下来的
    -0.86
    岀
    -0.85
    ～！
    -0.84
     after
    -0.84
    ｶ
    -0.84
    資料來源
    -0.84
    POSITIVE LOGITS
    他也
    1.09
     tools
    1.02
    也能
    1.01
     technology
    0.99
     também
    0.98
     available
    0.94
     знаю
    0.91
    也在
    0.91
    available
    0.90
     relationships
    0.90
    Activations Density 0.074%

    No Known Activations