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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4195
    Prev
    Next
    INDEX
    Explanations

    ancient migrations and human history

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

    The neuron activates on descriptions of archaeological digs or discoveries (e.g. sites, excavations, ancient campsites, artifacts).

    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
     imperson
    -0.77
     pretend
    -0.71
    SCHEDULE
    -0.70
    mock
    -0.69
    Bron
    -0.69
    Synd
    -0.68
     alab
    -0.68
    ticelli
    -0.67
     Troll
    -0.66
     TBD
    -0.66
    POSITIVE LOGITS
     migrations
    0.93
     migration
    0.91
     evidence
    0.90
     migrate
    0.87
     gentes
    0.85
    inqui
    0.85
     Clovis
    0.83
    }^{*}$
    0.82
    icolo
    0.80
    wander
    0.80
    Activations Density 0.027%

    No Known Activations