© 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. 84787
    Prev
    Next
    INDEX
    Explanations

    decisions and past actions

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

    The neuron is simply signaling very common (high‐frequency) tokens, regardless of their meaning.

    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
    まだ
    -0.90
     welcome
    -0.87
    Worst
    -0.86
    Beware
    -0.84
    続く
    -0.83
     hurry
    -0.82
    歡迎
    -0.82
     Descent
    -0.81
     their
    -0.81
     चुनें
    -0.81
    POSITIVE LOGITS
     decision
    1.98
     décision
    1.55
    decision
    1.46
     decided
    1.45
     decisions
    1.43
     Decision
    1.39
    Decision
    1.35
     decisão
    1.32
     decisione
    1.27
     decisión
    1.24
    Activations Density 0.124%

    No Known Activations