© 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. 31605
    Prev
    Next
    INDEX
    Explanations

    Nvidia GTX graphics card models

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

    The neuron fires strongly on numeric tokens—especially hardware counts or model numbers (e.g. GPU counts and GPU model identifiers).

    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
    ционно
    -0.84
    UGO
    -0.73
    おきます
    -0.73
    ➓
    -0.71
     证书
    -0.71
    丄
    -0.70
     profissional
    -0.68
    kyat
    -0.68
    PAP
    -0.67
     Espace
    -0.67
    POSITIVE LOGITS
     посвящен
    0.79
     GTX
    0.76
     Titan
    0.73
     хозя
    0.72
    GTX
    0.71
     kingdoms
    0.70
     loan
    0.69
    modeling
    0.69
    signable
    0.68
     cards
    0.67
    Activations Density 0.021%

    No Known Activations