© 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. 22-GEMMASCOPE-RES-131K
    7. 69177
    Prev
    Next
    INDEX
    Explanations

    data structures, lists, or JSON

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

    The neuron chiefly detects standalone numeric tokens (i.e. 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_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
    無論
    -1.16
     manifestly
    -1.10
     fator
    -1.05
    東南
    -1.05
    ．．
    -1.01
     Sovi
    -1.00
     仕事
    -1.00
    因為
    -0.99
     искрен
    -0.99
     bienvenue
    -0.98
    POSITIVE LOGITS
     moviliz
    1.05
    провод
    0.96
    看一下
    0.95
     siedz
    0.94
    ⻑
    0.93
     uppdater
    0.93
    xff
    0.93
     coloque
    0.93
     mempel
    0.92
     encontra
    0.91
    Activations Density 0.434%

    No Known Activations