© 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. 60605
    Prev
    Next
    INDEX
    Explanations

    namespace detail

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

    This neuron detects C++ scope‐resolution tokens (the “::” in qualified 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
    monary
    -0.95
    izace
    -0.88
    kitten
    -0.87
     what
    -0.87
    家が
    -0.85
     réputation
    -0.83
    lepaskan
    -0.83
     came
    -0.82
    geox
    -0.82
    aneous
    -0.81
    POSITIVE LOGITS
    detail
    1.31
     detail
    1.11
     details
    1.02
    DETAIL
    1.01
     MAKING
    0.98
     amazingly
    0.96
    details
    0.96
    apprendre
    0.93
    ˂
    0.93
     Detail
    0.93
    Activations Density 0.048%

    No Known Activations