© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99764
    Prev
    Next
    INDEX
    Explanations

    soldiers and men

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

    The neuron reliably picks out quantitative expressions—numbers and count words (e.g. numeric dates, troop/ship/personnel counts) that convey numerical data.

    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
     mempelajari
    -1.02
     menangkap
    -0.99
     mengembangkan
    -0.98
     menekan
    -0.96
     tersenyum
    -0.94
     memasang
    -0.94
     mengumpulkan
    -0.91
     menikmati
    -0.90
     mengingatkan
    -0.90
     menangani
    -0.89
    POSITIVE LOGITS
     men
    3.55
    men
    2.22
     hommes
    2.13
     Men
    1.97
     soldiers
    1.96
    Men
    1.91
     MEN
    1.73
     uomini
    1.73
     boys
    1.70
     homens
    1.70
    Activations Density 0.043%

    No Known Activations