© 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. 22-GEMMASCOPE-RES-131K
    4. 13336
    Prev
    Next
    INDEX
    Explanations

    data and services

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

    This neuron strongly activates on individual code or API identifiers—especially capitalized type, class, or function 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_22/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
     a
    -1.19
    cress
    -1.07
     because
    -1.07
    #%%
    
    -1.05
     for
    -0.98
     not
    -0.95
     anything
    -0.93
    都係
    -0.93
     it
    -0.93
     so
    -0.93
    POSITIVE LOGITS
     orquesta
    1.18
    orphic
    1.14
    𝔤
    1.13
    几人
    1.11
    很赞
    1.10
    ͤ
    1.09
     чехол
    1.08
    ellular
    1.08
     bằng
    1.05
    minaire
    1.05
    Activations Density 0.019%

    No Known Activations