© 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. 84694
    Prev
    Next
    INDEX
    Explanations

    redistribution and permission

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

    The neuron primarily fires on tokens that are numeric (digit‐containing) values.

    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
     αγα
    -0.75
    bant
    -0.71
    วน
    -0.70
    скет
    -0.70
    forName
    -0.70
     λογ
    -0.69
    ੦
    -0.69
    www
    -0.69
     v
    -0.68
     выбран
    -0.68
    POSITIVE LOGITS
    样式
    0.69
    Oss
    0.68
     budapest
    0.68
     dragonfly
    0.68
     ③
    0.68
     dreht
    0.67
    isNotNull
    0.67
    ковий
    0.67
    fileInfo
    0.66
    idad
    0.66
    Activations Density 0.027%

    No Known Activations