© 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. 55734
    Prev
    Next
    INDEX
    Explanations

    associating cycles or sections

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

    The neuron activates on numeric tokens (sequences of digits) 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
     generado
    -0.94
     préserver
    -0.82
    Xeno
    -0.81
    playable
    -0.80
     célè
    -0.80
    harmed
    -0.78
    deemed
    -0.77
    Pound
    -0.74
    romance
    -0.74
     réserver
    -0.73
    POSITIVE LOGITS
    lift
    1.05
     sections
    0.96
     lift
    0.93
     Lift
    0.85
    Lift
    0.82
    〜
    0.82
     data
    0.81
    extend
    0.81
    fiber
    0.80
     extending
    0.79
    Activations Density 0.052%

    No Known Activations