© 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. 34-GEMMASCOPE-RES-131K
    7. 60414
    Prev
    Next
    INDEX
    Explanations

    computer programs and programming

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

    The neuron fires most strongly on programming‐related terms (e.g. program, programming, software, debugging).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    يًا
    -0.84
    غرب
    -0.82
     troviamo
    -0.82
    zaken
    -0.80
     parteci
    -0.80
    ঙ
    -0.79
    зонта
    -0.78
    見えます
    -0.78
     vuole
    -0.77
    qtype
    -0.77
    POSITIVE LOGITS
     programming
    3.80
    programming
    3.03
     program
    3.03
     Programming
    2.86
     programs
    2.80
    Programming
    2.63
     coding
    2.59
     programmers
    2.52
    program
    2.52
    PROGRAM
    2.50
    Activations Density 0.235%

    No Known Activations