© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 97868
    Prev
    Next
    INDEX
    Explanations

    language constructs

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

    The neuron is tuned to detect numeric literals (tokens consisting of digits).

    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
     vieilles
    -1.05
     delicado
    -1.05
    幫忙
    -1.01
    tır
    -0.96
     doloroso
    -0.94
     mágico
    -0.94
    還在
    -0.93
     (()
    -0.93
    唸
    -0.93
     multiuso
    -0.91
    POSITIVE LOGITS
     !
    1.07
    !
    1.01
    жела
    1.00
    其
    0.94
     kembali
    0.93
    return
    0.93
     its
    0.91
     in
    0.91
    arschu
    0.91
     {
    
    0.90
    Activations Density 0.008%

    No Known Activations