© 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. 103465
    Prev
    Next
    INDEX
    Explanations

    units and technical abbreviations ending in L

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

    This neuron detects alphanumeric identifiers containing digits (e.g., gene/protein names or numeric codes).

    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
     fought
    -0.81
     corolla
    -0.75
    ange
    -0.75
     garner
    -0.74
     Erde
    -0.72
    EM
    -0.72
    حب
    -0.71
    ียด
    -0.69
     found
    -0.69
     голов
    -0.69
    POSITIVE LOGITS
     progreso
    0.86
     almacenamiento
    0.84
    naturally
    0.84
    ㄴ
    0.84
    蕺
    0.83
    où
    0.82
    oning
    0.80
    ЛЯ
    0.80
    significantly
    0.80
    WILL
    0.79
    Activations Density 0.084%

    No Known Activations