© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63787
    Prev
    Next
    INDEX
    Explanations

    military casualties and losses

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

    The neuron responds to numeric information—digits, figures, and number‐related tokens (dates, counts, statistics).

    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
     gefähr
    -0.91
     memutus
    -0.81
     regola
    -0.81
    ccm
    -0.80
    quez
    -0.80
     cuar
    -0.78
     peligro
    -0.78
    謀
    -0.78
    enging
    -0.77
    engkapi
    -0.76
    POSITIVE LOGITS
     casualties
    3.02
     losses
    2.94
     casualty
    2.39
     loss
    2.36
     Losses
    2.20
    losses
    2.16
    casual
    2.11
    Losses
    1.98
    Casual
    1.90
     Casual
    1.85
    Activations Density 0.028%

    No Known Activations