© 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. 10-GEMMASCOPE-RES-131K
    7. 128644
    Prev
    Next
    INDEX
    Explanations

    transportation systems and infrastructure

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

    The main thing this neuron does is detect mentions of transport or transportation-related terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     вашей
    -1.55
    يمكن
    -1.49
    4
    -1.46
     сегодня
    -1.45
    もっと
    -1.39
    íguez
    -1.38
     znajdziesz
    -1.30
     намного
    -1.30
     новых
    -1.29
    إذا
    -1.27
    POSITIVE LOGITS
     Then
    1.59
    ᵉ
    1.57
    nipeg
    1.46
     are
    1.40
    ünste
    1.34
     train
    1.31
    ческа
    1.30
    identes
    1.30
    irection
    1.30
    ficamente
    1.28
    Activations Density 0.045%

    No Known Activations