© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34912
    Prev
    Next
    INDEX
    Explanations

    Q commands

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

    The neuron fires on numeric literals (numbers) in code or text.

    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
     Leicestershire
    -0.87
     ミュ
    -0.85
    ルイ
    -0.84
     spoloč
    -0.83
     samtidigt
    -0.82
    诱惑
    -0.82
    書く
    -0.80
    バレンタイン
    -0.79
    轻易
    -0.79
     nether
    -0.79
    POSITIVE LOGITS
     Florida
    1.17
    ModelAdmin
    0.92
    winning
    0.86
     Orlando
    0.85
     оригинала
    0.84
     keywords
    0.83
     ami
    0.82
     imagens
    0.81
    Florida
    0.81
     investors
    0.79
    Activations Density 0.009%

    No Known Activations