© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92684
    Prev
    Next
    INDEX
    Explanations

    docker commands

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

    The neuron activates on numeric tokens—especially multi-digit numbers, years, percentages, and other standalone figures.

    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
     ára
    -1.02
    ₤
    -0.94
    })$
    -0.93
    预测
    -0.92
    fromCharCode
    -0.88
    strictEqual
    -0.87
    DotNetBar
    -0.86
    moveToNext
    -0.86
    fang
    -0.85
    __))
    -0.84
    POSITIVE LOGITS
    かと思います
    0.91
     pandemia
    0.90
     pandemic
    0.89
    COVID
    0.87
    しん
    0.86
    coronavirus
    0.85
    著書
    0.82
    🪶
    0.81
     covid
    0.81
     Meme
    0.80
    Activations Density 0.374%

    No Known Activations