© 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. 109115
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions; rather, instead

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

    The neuron specializes in picking out numeric tokens (e.g. years or multi‐digit numbers).

    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
     not
    -0.95
     precies
    -0.88
    }`}>
    -0.86
    tigkeits
    -0.80
     suéter
    -0.79
    árqu
    -0.79
     không
    -0.78
    Dabei
    -0.76
     apakah
    -0.75
    poptosis
    -0.75
    POSITIVE LOGITS
     rather
    6.78
     Rather
    5.81
    Rather
    5.78
    rather
    5.19
     plutôt
    4.97
     vielmehr
    4.38
    むしろ
    4.19
     piuttosto
    3.97
     скорее
    3.86
    而是
    3.77
    Activations Density 0.080%

    No Known Activations