© 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. 34-GEMMASCOPE-RES-131K
    7. 7150
    Prev
    Next
    INDEX
    Explanations

    technical documentation

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

    The neuron is triggered by multi‐digit numeric tokens (e.g. document or section 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_34/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
    bouncycastle
    -0.85
    ôtel
    -0.84
    nikon
    -0.82
     eorum
    -0.82
     cál
    -0.81
    憺
    -0.77
    loài
    -0.76
    peated
    -0.75
     araç
    -0.75
    lloworld
    -0.74
    POSITIVE LOGITS
    眉头
    0.92
     specification
    0.85
    ---
    0.83
    alias
    0.81
    setMinimum
    0.80
     stille
    0.78
    umentación
    0.77
    olar
    0.75
     inches
    0.75
    你这个
    0.75
    Activations Density 0.001%

    No Known Activations