© 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. 61079
    Prev
    Next
    INDEX
    Explanations

    existing things

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

    The neuron detects occurrences of the word “existing.”

    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
    3
    -1.57
    6
    -1.49
    7
    -1.42
    =“
    -1.35
     kepad
    -1.35
     arbe
    -1.29
    mian
    -1.24
    ᾐ
    -1.22
    mato
    -1.20
     Pada
    -1.20
    POSITIVE LOGITS
     current
    1.50
    existing
    1.44
     Current
    1.41
    current
    1.41
     existing
    1.34
    Current
    1.33
     Públicas
    1.30
     Worten
    1.27
    眼鏡
    1.27
    dịch
    1.26
    Activations Density 0.152%

    No Known Activations