© 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. 10-GEMMASCOPE-RES-131K
    7. 129584
    Prev
    Next
    INDEX
    Explanations

    different types of things

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

    The neuron is primarily detecting the word “different.”

    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
    having
    -1.61
     simpel
    -1.60
     épreuves
    -1.52
    anyone
    -1.41
     lij
    -1.38
     uly
    -1.36
    gier
    -1.35
     biet
    -1.34
    unfortunately
    -1.33
    possibly
    -1.32
    POSITIVE LOGITS
     encompassing
    1.44
     when
    1.43
     their
    1.42
     perplexing
    1.39
    いっぱ
    1.38
    czerw
    1.38
     people
    1.37
     on
    1.37
     during
    1.37
     haphazard
    1.35
    Activations Density 0.059%

    No Known Activations