© 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. 10-GEMMASCOPE-RES-131K
    7. 86494
    Prev
    Next
    INDEX
    Explanations

    animals like alpaca, llama, camel

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

    This neuron is detecting references to camelid animals, particularly alpacas and llamas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     victories
    -1.67
    豨
    -1.63
     zlep
    -1.63
     FÜR
    -1.62
    ൎ
    -1.60
    ⎆
    -1.57
    л
    -1.56
    :"-
    -1.55
    ”،
    -1.55
    ౧
    -1.55
    POSITIVE LOGITS
    {
    2.19
     Virtually
    1.65
    $
    1.55
    𝐊
    1.54
    しました
    1.52
     Focusing
    1.52
     Where
    1.51
    {'
    1.49
     Around
    1.48
    A
    1.47
    Activations Density 0.010%

    No Known Activations