© 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. 68086
    Prev
    Next
    INDEX
    Explanations

    brands and products

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

    The main thing this neuron does is spot mentions of specific product or brand model names.

    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
     it
    -1.80
     this
    -1.67
     its
    -1.66
    ynchronously
    -1.55
     will
    -1.55
     salão
    -1.47
     limpo
    -1.43
     sítio
    -1.37
     edifício
    -1.36
    diseases
    -1.31
    POSITIVE LOGITS
     résister
    1.60
    ೭
    1.58
    なども
    1.57
     but
    1.49
     niks
    1.48
     example
    1.45
     использованием
    1.44
     или
    1.41
     or
    1.41
     berharap
    1.38
    Activations Density 0.062%

    No Known Activations