© 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. 34-GEMMASCOPE-RES-131K
    4. 80920
    Prev
    Next
    INDEX
    Explanations

    video footage clips

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

    The neuron primarily activates on numerical tokens—sequences of digits.

    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
     for
    -1.01
     demos
    -0.88
    来
    -0.85
    demos
    -0.82
     PAGE
    -0.81
    ærk
    -0.80
     mock
    -0.79
     flask
    -0.77
    }$.
    -0.77
    uits
    -0.77
    POSITIVE LOGITS
     obtained
    1.18
     taken
    0.96
    ayangkan
    0.94
    ಆ
    0.90
    Noter
    0.89
     Obtained
    0.88
     Fuzzy
    0.88
     uintptr
    0.85
     televisiva
    0.84
     pensent
    0.84
    Activations Density 0.027%

    No Known Activations