© 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. 34-GEMMASCOPE-RES-131K
    4. 111097
    Prev
    Next
    INDEX
    Explanations

    function.include failed

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

    The neuron fires on programming‐style metadata and markup (e.g. tool names, version numbers, compiler or warning messages, bracketed identifiers)—in other words, it detects code/documentation artifacts rather than natural‐language text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    뱅
    -0.78
    ACKNOWLEDGMENT
    -0.77
    ädigung
    -0.71
     Wolfs
    -0.70
     navigateur
    -0.68
     Beep
    -0.68
    spend
    -0.66
     thờ
    -0.66
     HELLO
    -0.66
    nath
    -0.65
    POSITIVE LOGITS
    늬
    0.64
    qq
    0.63
    veni
    0.63
    챔
    0.63
    讐
    0.63
    дава
    0.62
    cosh
    0.62
     Maha
    0.62
     tedy
    0.61
    许久
    0.61
    Activations Density 0.073%

    No Known Activations