© 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. 3378
    Prev
    Next
    INDEX
    Explanations

    sales and business performance

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

    The neuron flags occurrences of quantitative metrics or numeric performance indicators (e.g. sales figures, registration counts, traffic volumes).

    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
     zdan
    -1.03
     worsening
    -0.98
     arric
    -0.92
    Reducing
    -0.91
     排骨
    -0.89
    Offer
    -0.88
    ⠨
    -0.87
     deği
    -0.86
     Precio
    -0.85
    árbol
    -0.85
    POSITIVE LOGITS
     steady
    1.30
     healthy
    1.26
     January
    1.20
     October
    1.19
    steady
    1.16
     volume
    1.10
     strong
    1.09
     November
    1.05
     Steady
    1.04
     growth
    1.02
    Activations Density 0.052%

    No Known Activations