© 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. 22-GEMMASCOPE-RES-131K
    7. 70621
    Prev
    Next
    INDEX
    Explanations

    programming concepts and constructs

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

    This neuron fires strongly on “Buffer”-related terms (especially in “Buffer Overflow” contexts) in code comments and identifiers.

    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
     their
    -1.80
     joyas
    -1.59
     tett
    -1.46
     bicicletas
    -1.46
     lentejuelas
    -1.45
     in
    -1.44
     supremely
    -1.38
    🐾
    -1.38
    日起
    -1.38
     cleverly
    -1.36
    POSITIVE LOGITS
    <bos>
    1.91
     diversos
    1.51
    そして
    1.51
    both
    1.49
    ちなみに
    1.46
    p
    1.46
     alcune
    1.45
    u
    1.42
    particularly
    1.40
     dieselben
    1.38
    Activations Density 0.022%

    No Known Activations