© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27953
    Prev
    Next
    INDEX
    Explanations

    Jill Dixon, Mouse models

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

    programming-related verbs like "render", "return", and "yield" in code snippets.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on MVC controller action code—specifically tokens like “Index,” “return,” “View,” and “render” that define and return views.

    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
     nuov
    -1.30
    に行く
    -1.27
    に入れる
    -1.22
    以外の
    -1.20
    様に
    -1.15
     and
    -1.13
    /*!
    
    -1.13
     Songtext
    -1.09
    に戻る
    -1.07
    際の
    -1.06
    POSITIVE LOGITS
    があります
    1.32
    ériques
    1.26
    ネー
    1.25
    Obrázky
    1.20
     冊
    1.17
    אני
    1.13
    ikations
    1.13
    ですが
    1.13
    辑
    1.12
    Татьяна
    1.11
    Activations Density 0.000%

    No Known Activations