© 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. 66679
    Prev
    Next
    INDEX
    Explanations

    data type keywords

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

    The neuron detects programming identifiers—especially function or method names and type‐cast tokens in code.

    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
     for
    -1.39
    えず
    -1.13
     with
    -1.13
     retten
    -1.09
    瑋
    -1.07
     where
    -1.05
    てもら
    -1.01
     on
    -0.98
    centerTitle
    -0.98
    钰
    -0.98
    POSITIVE LOGITS
    作成
    1.04
     miei
    1.04
    ۔
    1.04
    采购
    1.01
    lüsse
    0.98
    她的
    0.96
    ں
    0.94
    有很多
    0.94
    以前
    0.92
    এ
    0.91
    Activations Density 0.003%

    No Known Activations