© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27359
    Prev
    Next
    INDEX
    Explanations

    numbers and court

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

    The neuron selectively activates on standalone numeric tokens (i.e. any numbers appearing in the text).

    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
     predomin
    -0.95
    톡
    -0.84
    ：……
    -0.84
     getBase
    -0.84
    Обу
    -0.83
     although
    -0.82
    앞
    -0.81
     from
    -0.80
    Ис
    -0.80
    Those
    -0.79
    POSITIVE LOGITS
    minster
    1.03
    }\}
    0.91
    ͛
    0.90
     amarela
    0.90
    Lucia
    0.89
    agerie
    0.88
    Literacy
    0.87
     antiguos
    0.86
     vermelha
    0.86
     gän
    0.86
    Activations Density 0.097%

    No Known Activations