© 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. 12723
    Prev
    Next
    INDEX
    Explanations

    comparative genomic hybridization

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

    prompts asking for user input in programming code, especially those ending with colons or question marks.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is triggered by numeric literals (digits) appearing in code snippets.

    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
    和
    -1.05
    opie
    -0.96
     повіт
    -0.94
    生存
    -0.90
     comprise
    -0.88
    need
    -0.88
    𖣔
    -0.87
     comprised
    -0.85
     мебели
    -0.83
    lation
    -0.83
    POSITIVE LOGITS
    Może
    0.98
    Минусы
    0.95
    basement
    0.93
     regardant
    0.92
     Divis
    0.92
    場所に
    0.91
     '=',
    0.91
     Castilla
    0.88
     evangé
    0.88
     respondents
    0.87
    Activations Density 0.002%

    No Known Activations