© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14062
    Prev
    Next
    INDEX
    Explanations

    naming convention

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

    The neuron specifically fires on occurrences of the word “naming,” particularly in discussions of naming conventions.

    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
    {
    -2.64
     '';
    -2.42
     or
    -2.33
    とその
    -2.31
     ''
    -2.30
     の
    -2.27
     \
    -2.25
    ]
    -2.13
    *
    -2.08
    (
    -2.00
    POSITIVE LOGITS
    大腿
    2.39
    銪
    2.28
    鋨
    2.25
    But
    2.23
     республики
    2.22
    ܆
    2.17
     فرش
    2.14
    嚒
    2.14
    </strong>
    2.13
     strane
    2.13
    Activations Density 0.010%

    No Known Activations