© 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. 10-GEMMASCOPE-RES-131K
    4. 103980
    Prev
    Next
    INDEX
    Explanations

    database query methods

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

    method names in code that retrieve data by identifier or query parameter.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    Explanation of neuron 4 behavior: the main thing this neuron does is find data-access method calls beginning with “find” (e.g. findById, findByEmail, findAll).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     iNdEx
    -1.46
    brtc
    -1.38
    woners
    -1.38
    приятие
    -1.37
     Infór
    -1.36
     ferien
    -1.31
     geplaatst
    -1.31
     stol
    -1.31
     ruf
    -1.30
    内の
    -1.29
    POSITIVE LOGITS
    Other
    1.77
    There
    1.48
    The
    1.44
    -
    1.42
    Using
    1.42
    .
    1.38
     häufigsten
    1.38
    Perhaps
    1.37
    Despite
    1.35
     Other
    1.34
    Activations Density 0.005%

    No Known Activations