© 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. 9342
    Prev
    Next
    INDEX
    Explanations

    increment or decrement operations

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

    The neuron flags uses of the C-style increment/decrement operators (i.e. “++” or “--”).

    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
     alice
    -0.90
    İ
    -0.88
    P
    -0.88
    🌏
    -0.87
    ga
    -0.87
     Turkey
    -0.86
    ع
    -0.86
    پ
    -0.85
    Г
    -0.85
    せ
    -0.84
    POSITIVE LOGITS
    ئلة
    0.93
     dacă
    0.91
     życie
    0.88
    ندما
    0.88
    braith
    0.86
    warted
    0.86
    היו
    0.84
    Disciplina
    0.84
    Aves
    0.84
    Bibliografie
    0.83
    Activations Density 0.003%

    No Known Activations