© 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. 94141
    Prev
    Next
    INDEX
    Explanations

    comparing alternatives

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

    The neuron fires on C++ equality‐comparison operator definitions (i.e. occurrences of “operator ==” and its related 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_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
    uatu
    -0.96
     Söhne
    -0.89
    Lebih
    -0.88
    бые
    -0.88
     області
    -0.87
    Processors
    -0.86
    ύτε
    -0.84
    ASHINGTON
    -0.84
     Zurück
    -0.84
     дії
    -0.84
    POSITIVE LOGITS
     other
    3.81
    other
    2.84
     another
    2.56
    Other
    2.55
     Other
    2.42
     autre
    2.38
     others
    2.31
     других
    2.25
     autres
    2.20
     otros
    2.17
    Activations Density 0.021%

    No Known Activations