© 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. 92112
    Prev
    Next
    INDEX
    Explanations

    major and minor

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

    The neuron strongly activates on tokens containing numbers (numeric sequences).

    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
     tiered
    -0.88
    STT
    -0.80
    星星
    -0.77
    笄
    -0.76
    bama
    -0.75
     obyvateľov
    -0.75
    理工
    -0.75
     disbursements
    -0.74
    ྀ
    -0.73
     Maybe
    -0.73
    POSITIVE LOGITS
    minor
    1.00
    Major
    0.99
    Minor
    0.96
    major
    0.93
     minor
    0.91
     Major
    0.84
     maj
    0.81
     カップ
    0.79
     
    0.79
     Minor
    0.78
    Activations Density 0.025%

    No Known Activations