© 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. 1055
    Prev
    Next
    INDEX
    Explanations

    ancient artifacts, sites, and trade

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

    The neuron flags detailed archaeological and prehistoric research terminology—especially period names (e.g. “Neolithic,” “Bronze Age”) and specialized methods or finds (e.g. “isotope analysis,” “human bone,” “stone axe”).

    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
     historical
    -0.93
     metodi
    -0.83
     modernized
    -0.82
     нынеш
    -0.81
    낌
    -0.81
     citi
    -0.80
     simpto
    -0.79
    Historical
    -0.79
    zied
    -0.79
    现有
    -0.78
    POSITIVE LOGITS
     elites
    1.16
    elite
    1.06
     elite
    1.05
     ideology
    0.95
     reuse
    0.91
     consumir
    0.85
     Elite
    0.85
     households
    0.84
     chaine
    0.84
     ceramic
    0.82
    Activations Density 0.034%

    No Known Activations