© 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. 23876
    Prev
    Next
    INDEX
    Explanations

    awards and rankings

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

    The neuron responds to numeric tokens—especially years, dates, and other statistics.

    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
    Inicial
    -0.88
    players
    -0.78
    Ꮪ
    -0.77
    ンピース
    -0.75
    𝒉
    -0.75
    Keep
    -0.74
     inherently
    -0.73
    marketplace
    -0.73
     raggiung
    -0.72
     achieve
    -0.72
    POSITIVE LOGITS
    Communist
    0.85
    
    0.84
     talentos
    0.84
     impresora
    0.83
     escolares
    0.83
    )}_{
    0.82
     Maschine
    0.81
    苡
    0.80
    unes
    0.79
     múltip
    0.79
    Activations Density 0.018%

    No Known Activations