© 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. 34-GEMMASCOPE-RES-131K
    7. 45747
    Prev
    Next
    INDEX
    Explanations

    AM PDT namespaces

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

    The neuron strongly responds to code‐related syntax elements (e.g. class/extends/Controller keywords, braces, namespace/package declarations, and similar programming punctuation).

    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
    instancetype
    -0.90
     tragen
    -0.85
     AssemblyVersion
    -0.84
     Wikime
    -0.83
     سينما
    -0.82
    .%
    -0.75
     Animator
    -0.75
    lisis
    -0.74
    گذار
    -0.72
    インテリア
    -0.72
    POSITIVE LOGITS
    ájá
    0.86
    Chimp
    0.75
     tankers
    0.73
    ABD
    0.73
    GPT
    0.73
     composto
    0.73
     постанов
    0.72
    ᄒ
    0.71
     ダン
    0.71
    左手
    0.71
    Activations Density 0.001%

    No Known Activations