© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15037
    Prev
    Next
    INDEX
    Explanations

    lists of items or places

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

    The neuron specializes in spotting numeric tokens—i.e. any words or phrases containing digits such as quantities, measurements, or counts.

    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
     tuc
    -0.93
     RÉ
    -0.92
    Diem
    -0.90
    ソウル
    -0.89
    çok
    -0.89
    茛
    -0.88
    Enviado
    -0.88
    receta
    -0.85
     étan
    -0.85
    ätten
    -0.84
    POSITIVE LOGITS
    W
    0.92
    甚至是
    0.92
    ep
    0.89
    UTIVE
    0.89
     both
    0.85
    even
    0.85
     अपनी
    0.84
     пев
    0.82
    ev
    0.82
    ทั้ง
    0.82
    Activations Density 0.028%

    No Known Activations