© 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. 59787
    Prev
    Next
    INDEX
    Explanations

    walk into the

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

    The neuron strongly responds to descriptions of someone entering a place, especially the phrase “walked into.”

    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
    6
    -2.91
    2
    -2.27
    3
    -2.25
    4
    -2.19
    9
    -2.11
    7
    -1.96
    8
    -1.78
    1
    -1.77
    no
    -1.77
    橚
    -1.76
    POSITIVE LOGITS
    aumento
    2.09
     one
    1.96
    brinco
    1.76
    yaitu
    1.75
     as
    1.73
     a
    1.73
    dengan
    1.66
     sparkling
    1.66
     by
    1.62
    seperti
    1.62
    Activations Density 0.012%

    No Known Activations