© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14202
    Prev
    Next
    INDEX
    Explanations

    upload, submit, posting

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

    The neuron fires whenever it sees numeric literals (digits or 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_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
    Cond
    -0.97
     ź
    -0.84
     eaux
    -0.81
    ufort
    -0.80
    posY
    -0.79
    
    -0.79
     Sampling
    -0.76
     mê
    -0.76
     extracting
    -0.75
    Ore
    -0.74
    POSITIVE LOGITS
     submission
    1.50
     submit
    1.39
     submitted
    1.34
    提交
    1.34
     submitting
    1.29
    submit
    1.09
     posting
    1.09
    Submitting
    1.07
     submissions
    1.02
     submits
    1.02
    Activations Density 0.129%

    No Known Activations