© 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. 70569
    Prev
    Next
    INDEX
    Explanations

    section headers or labels

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

    The neuron strongly activates on numeric tokens (digits, scores, bracketed seed numbers) in match results.

    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
     konsult
    -1.01
     precedenti
    -1.00
    kammer
    -0.98
     хорошие
    -0.97
    pregunt
    -0.94
    ÍNDICE
    -0.94
    nữ
    -0.93
    ່
    -0.93
     konsumen
    -0.90
    –¿
    -0.88
    POSITIVE LOGITS
    лада
    0.86
    zieć
    0.84
     сзади
    0.83
    DEBUG
    0.83
     proven
    0.82
     among
    0.82
     autre
    0.82
    myr
    0.82
    ת
    0.82
     otro
    0.81
    Activations Density 0.000%

    No Known Activations