© 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. 11255
    Prev
    Next
    INDEX
    Explanations

    getter and HttpGet

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

    the word "getter" or variations of it in programming contexts.

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

    The neuron fires on occurrences of the substring “getter” (including “getters” and “HttpGet”), i.e. it detects “getter”-related tokens.

    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
    All
    -2.64
     wirk
    -2.53
    no
    -2.38
     بودند
    -2.33
    just
    -2.30
    is
    -2.30
    焿
    -2.28
    5
    -2.27
     guna
    -2.22
     ※
    -2.22
    POSITIVE LOGITS
    tedì
    3.00
     był
    2.50
    泚
    2.25
    ꯳
    2.25
    '
    2.23
     únicamente
    2.23
    隍
    2.19
    
    2.11
     était
    2.09
    ,:]
    2.06
    Activations Density 0.001%

    No Known Activations