© 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. 90670
    Prev
    Next
    INDEX
    Explanations

    right, |

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

    The neuron strongly activates on numeric literals (digits or numbers) appearing in the 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
     créditos
    -1.03
    bolso
    -1.00
     akci
    -0.93
     ekolog
    -0.92
    caucasian
    -0.87
    cerv
    -0.86
     encuent
    -0.86
     silencioso
    -0.85
     kym
    -0.85
    yym
    -0.85
    POSITIVE LOGITS
    |
    0.92
     коне
    0.77
     сих
    0.76
    raltar
    0.76
    atique
    0.75
    剩下
    0.75
    יי
    0.74
    this
    0.74
    [,]
    0.73
    Pers
    0.72
    Activations Density 0.000%

    No Known Activations