© 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. 10-GEMMASCOPE-RES-131K
    7. 90728
    Prev
    Next
    INDEX
    Explanations

    name =

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

    The neuron fires on occurrences of the identifier “name” when used in code or configuration (e.g. in field or attribute assignments like name='…').

    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
     become
    -1.44
     only
    -1.42
    atação
    -1.41
     tylko
    -1.37
    プロセス
    -1.35
     acknowledges
    -1.34
     prominently
    -1.34
    gencias
    -1.29
     gedurende
    -1.29
     consumes
    -1.28
    POSITIVE LOGITS
     =
    1.83
    .
    1.59
    嚶
    1.58
    %;
    1.50
    </strong>
    1.47
    KommentareTeilen
    1.43
    )
    1.42
    ㈬
    1.41
    instead
    1.41
    不是
    1.41
    Activations Density 0.001%

    No Known Activations