© 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. 55966
    Prev
    Next
    INDEX
    Explanations

    code annotations and namespaces

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

    The neuron is detecting tokens that are parts of code identifiers—especially CamelCase class or namespace names.

    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
    ::*;
    -0.96
    FUNC
    -0.91
    reten
    -0.88
    Kaieteur
    -0.87
    uksen
    -0.83
    kosť
    -0.82
    Eksteraj
    -0.81
    앗
    -0.79
     periodontal
    -0.79
    ум
    -0.76
    POSITIVE LOGITS
    に関しては
    0.86
    除去
    0.85
    erson
    0.76
    Gry
    0.75
     структура
    0.74
    lowy
    0.74
     travailler
    0.73
    があって
    0.73
     dikenal
    0.72
     froh
    0.72
    Activations Density 0.008%

    No Known Activations