© 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. 65434
    Prev
    Next
    INDEX
    Explanations

    consistency or daily routine

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

    The neuron strongly activates on numeric tokens (numbers and quantities).

    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
     finalidad
    -0.83
    uição
    -0.82
    之时
    -0.81
    ể
    -0.81
    bebasan
    -0.79
    pañas
    -0.76
    ukunfts
    -0.76
     Cantor
    -0.75
     OBJECTIVES
    -0.75
    etate
    -0.74
    POSITIVE LOGITS
     consistency
    4.09
     consistent
    3.84
     Consistency
    3.61
    Consistency
    3.55
    consistent
    3.55
    consistency
    3.50
    Consistent
    3.25
     Consistent
    3.13
     consistently
    2.91
     inconsistent
    2.56
    Activations Density 0.034%

    No Known Activations