© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27984
    Prev
    Next
    INDEX
    Explanations

    third place medal

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

    The neuron fires on mentions of third‐place or bronze‐medal finishes in competitions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ítulo
    -1.02
    ---|---|
    -0.99
    தி
    -0.98
    YI
    -0.97
    ovu
    -0.97
    jke
    -0.87
     kilometr
    -0.85
     вже
    -0.85
    ANCH
    -0.84
    utom
    -0.84
    POSITIVE LOGITS
    すべき
    1.10
    幾個
    0.99
     sätta
    0.96
     confirmó
    0.95
     uzak
    0.94
     assistir
    0.93
    BorderSize
    0.93
     باقی
    0.93
     entregó
    0.93
     any
    0.91
    Activations Density 0.003%

    No Known Activations