© 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. 92968
    Prev
    Next
    INDEX
    Explanations

    species' geographic origins

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

    geographic locations, particularly when describing the habitat or distribution of species.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numerical tokens (years, counts, measurements) in the text.

    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
    Pranala
    -1.10
     diinginkan
    -1.03
    виа
    -1.02
    *****/
    -1.00
     شاهد
    -1.00
    opheles
    -0.99
    WebView
    -0.98
     antar
    -0.98
    UMENT
    -0.97
    . 
    -0.97
    POSITIVE LOGITS
    holo
    1.02
     bisexual
    0.97
     localities
    0.94
    ,:);
    0.94
    twór
    0.90
     sensu
    0.89
     संग
    0.88
     lecz
    0.88
    bion
    0.87
     western
    0.87
    Activations Density 0.093%

    No Known Activations