© 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. 75832
    Prev
    Next
    INDEX
    Explanations

    was Dean

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

    The neuron strongly activates on tokens that are purely numeric (digit 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
     intrinsically
    -0.92
     while
    -0.87
     relatively
    -0.86
     reduced
    -0.84
     compelling
    -0.84
     further
    -0.83
     without
    -0.83
     out
    -0.82
     bassi
    -0.80
     long
    -0.79
    POSITIVE LOGITS
    urface
    1.15
    begins
    1.06
     Taehyung
    1.05
    feels
    1.01
    Öl
    0.99
    causes
    0.98
    Kaynak
    0.98
     مشابه
    0.96
     Graphics
    0.94
    netje
    0.93
    Activations Density 0.001%

    No Known Activations