© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35647
    Prev
    Next
    INDEX
    Explanations

    Q: or Report:

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

    The main thing this neuron does is detect occurrences of the literal word “path.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.37
     even
    -1.27
    calips
    -1.22
     anything
    -1.05
     和
    -1.04
    ==""){
    -1.03
    !#
    -1.02
     berapa
    -1.00
    :>
    -1.00
     нагруз
    -0.99
    POSITIVE LOGITS
    raltar
    1.18
     Insgesamt
    1.17
    biendo
    1.16
     Besonders
    1.13
    邹
    1.12
    Mejor
    1.10
     Dennoch
    1.10
     Trotzdem
    1.09
    Gön
    1.09
    Ingredi
    1.08
    Activations Density 0.000%

    No Known Activations