© 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. 34-GEMMASCOPE-RES-131K
    7. 11768
    Prev
    Next
    INDEX
    Explanations

    voyage and trip abroad

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

    The neuron is detecting very common, high‐frequency words (i.e. tokens that appear most often in text).

    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
     dizaine
    -0.97
     profusely
    -0.94
     allegiance
    -0.93
     GetEnumerator
    -0.93
     lightly
    -0.93
     namely
    -0.89
    ͌
    -0.88
     regain
    -0.88
     though
    -0.85
     havoc
    -0.85
    POSITIVE LOGITS
     frameworks
    1.31
     individuals
    1.29
     harmed
    1.15
    Individuals
    1.15
     contempl
    1.14
    individuals
    1.12
     referenced
    1.11
    出色
    1.02
     framework
    1.01
    바
    1.01
    Activations Density 0.031%

    No Known Activations