© 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. 119184
    Prev
    Next
    INDEX
    Explanations

    aircraft designations and types

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

    This neuron detects alphanumeric model or designation codes (letter–digit sequences, often hyphenated) as used for military aircraft and related equipment.

    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
    昔の
    -0.93
    ものです
    -0.92
     Recommended
    -0.88
     Another
    -0.85
    出于
    -0.85
    きち
    -0.84
     W
    -0.83
     and
    -0.83
    為に
    -0.83
     Then
    -0.82
    POSITIVE LOGITS
    ！(
    1.02
    ۱
    1.00
    sonian
    0.99
    ﾚ
    0.97
    してました
    0.96
    始め
    0.96
    bagai
    0.96
    ticos
    0.94
     vérit
    0.94
    yorum
    0.94
    Activations Density 0.026%

    No Known Activations