© 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. 110736
    Prev
    Next
    INDEX
    Explanations

    get methods

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

    method calls that retrieve or access data, particularly getter methods in programming code.

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

    The neuron fires on JavaScript or Java method calls beginning with “get” (i.e., getter-style method 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_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
    i
    -2.75
    s
    -2.47
     sosial
    -2.23
    おはようございます
    -2.14
    tifies
    -2.09
    𓋼
    -2.08
    you
    -2.06
    on
    -1.98
    that
    -1.97
     baut
    -1.97
    POSITIVE LOGITS
    '
    3.02
    
    2.27
     eer
    2.25
    boîte
    2.22
    chambre
    2.20
     nebst
    2.17
    遭受
    2.16
     Furthermore
    2.13
    ichia
    2.11
    stray
    2.11
    Activations Density 0.007%

    No Known Activations