© 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. 7226
    Prev
    Next
    INDEX
    Explanations

    language specific terms

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

    The neuron strongly activates on tokens containing numeric values or digits (e.g. measurements or counts).

    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
     and
    -1.18
    ongiorno
    -1.00
     about
    -0.98
     expanded
    -0.97
    ienze
    -0.95
    '
    -0.94
     generazione
    -0.93
    </em>
    -0.92
     parteci
    -0.91
    栃木
    -0.90
    POSITIVE LOGITS
     blanche
    1.20
     visuel
    1.19
     román
    1.19
     vernis
    1.18
     ٢
    1.18
     farine
    1.15
     pomme
    1.13
     lampe
    1.13
     murale
    1.13
    inig
    1.11
    Activations Density 0.238%

    No Known Activations