© 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. 34-GEMMASCOPE-RES-131K
    7. 1470
    Prev
    Next
    INDEX
    Explanations

    words starting with Fac

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

    The neuron fires strongly on any token containing the subword “fac” (e.g. Facel-Vega, Facets, Faced, facilitation), i.e. it detects the “fac” prefix.

    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
     Agricultura
    -0.81
    体会
    -0.78
     veroor
    -0.78
     garantia
    -0.77
    ASTE
    -0.75
    解決
    -0.75
    EOL
    -0.73
    +(\
    -0.72
    結構
    -0.72
    と思っていた
    -0.72
    POSITIVE LOGITS
     Fac
    1.89
     fac
    1.88
    fac
    1.84
    Fac
    1.76
     FAC
    1.67
    FAC
    1.54
     fak
    1.39
     Фа
    1.19
    facet
    1.16
     фа
    1.11
    Activations Density 0.016%

    No Known Activations