© 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. 68912
    Prev
    Next
    INDEX
    Explanations

    introducing lists or sequences

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

    The neuron detects cue words that introduce or point to lists and examples (e.g. “following,” “examples,” “below,” “illustrative”).

    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
     a
    -1.77
     then
    -1.74
    derdag
    -1.35
    Then
    -1.34
    Kemudian
    -1.28
    五日
    -1.27
    igree
    -1.27
    을
    -1.24
    ewear
    -1.24
    ")
    -1.24
    POSITIVE LOGITS
     naszych
    1.57
     diferite
    1.44
     naszego
    1.40
    ategoria
    1.38
     franceses
    1.35
     våra
    1.35
     oseb
    1.34
     our
    1.32
     nedan
    1.31
     urbain
    1.30
    Activations Density 0.048%

    No Known Activations