© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62706
    Prev
    Next
    INDEX
    Explanations

    supply shortages and delays

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

    The neuron fires on numerical and quantity expressions (e.g. digits, measures, 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_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
     spender
    -0.87
    ☁
    -0.85
     degeneration
    -0.83
    毎年
    -0.83
     skóry
    -0.83
    每年
    -0.81
    Pound
    -0.80
    🤓
    -0.79
    SAV
    -0.79
    Ἄ
    -0.78
    POSITIVE LOGITS
     supply
    3.02
    supply
    2.33
     Supply
    2.27
     shortages
    2.25
    Supply
    2.20
     SUPPLY
    1.84
     shortage
    1.76
     suppliers
    1.70
    供应
    1.70
     supplier
    1.69
    Activations Density 0.017%

    No Known Activations