© 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. 97881
    Prev
    Next
    INDEX
    Explanations

    numerical data and units

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

    The neuron fires on numeric tokens (numbers, percentages, and other numeral sequences).

    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
    外国
    -0.92
     said
    -0.92
     długość
    -0.91
    にします
    -0.91
     noticeable
    -0.91
     With
    -0.91
     these
    -0.90
    据
    -0.90
    をします
    -0.90
    رحلة
    -0.90
    POSITIVE LOGITS
    ichert
    1.07
     weaves
    1.05
     agir
    1.05
    えもん
    1.03
     år
    1.02
     elever
    1.01
    pm
    1.00
    irée
    0.98
     vatten
    0.98
    athered
    0.98
    Activations Density 0.063%

    No Known Activations