© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108149
    Prev
    Next
    INDEX
    Explanations

    data parameters and values

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

    The neuron fires on numeric tokens—i.e. digit‐only strings or numbers (like “864”, “428”, “0”, etc.).

    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
    糟糕
    -0.77
    Rast
    -0.75
     дыха
    -0.73
    {
    -0.72
    毎日
    -0.71
     nhiêu
    -0.69
     rodin
    -0.69
     unconnected
    -0.68
     aptly
    -0.68
    𝓽
    -0.66
    POSITIVE LOGITS
    stations
    0.98
    observations
    0.89
     internes
    0.86
     WOOD
    0.85
    processes
    0.84
    Obs
    0.84
     MARINE
    0.83
    marine
    0.82
    ttl
    0.82
     MARIE
    0.81
    Activations Density 0.009%

    No Known Activations