© 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. 79510
    Prev
    Next
    INDEX
    Explanations

    start of code or commands

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

    The neuron fires on tokens that are purely numeric (digit sequences), 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
     gavetas
    -1.20
    análisis
    -1.10
    drück
    -1.03
    ressee
    -1.00
    bestimm
    -0.98
    Método
    -0.97
    Jueves
    -0.97
     обратить
    -0.96
     potra
    -0.96
     apto
    -0.94
    POSITIVE LOGITS
    Then
    1.01
     actuelles
    0.98
    しかも
    0.95
    ROGEN
    0.94
     It
    0.93
     européennes
    0.92
    register
    0.92
    ですが
    0.91
     IN
    0.90
    gede
    0.89
    Activations Density 0.000%

    No Known Activations