© 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. 10-GEMMASCOPE-RES-131K
    7. 101904
    Prev
    Next
    INDEX
    Explanations

    including but not limited to

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

    The neuron fires on occurrences of the word “including,” i.e. it detects list-introduction tokens.

    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
    一旁
    -1.73
    一只
    -1.64
     perro
    -1.64
    旁边的
    -1.63
    IJ
    -1.62
     eser
    -1.61
    一旁的
    -1.61
     ܙ
    -1.56
     ſever
    -1.55
     humo
    -1.53
    POSITIVE LOGITS
    1
    1.82
     because
    1.71
     with
    1.69
     where
    1.59
     solchen
    1.57
     on
    1.49
     taking
    1.49
     häufig
    1.47
     considerazione
    1.44
     use
    1.43
    Activations Density 0.030%

    No Known Activations