© 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. 20260
    Prev
    Next
    INDEX
    Explanations

    succession, getDate, NaCl

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

    The neuron is highly sensitive to occurrences of the word “succession.”

    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
     soste
    -2.38
    孥
    -2.30
    !’
    -2.28
     ۸
    -2.23
    —”
    -2.19
     โดย
    -2.16
     scattata
    -2.16
    泐
    -2.16
     parec
    -2.16
     nuov
    -2.14
    POSITIVE LOGITS
    "
    3.16
    {
    2.58
     he
    2.48
    '
    2.41
     \
    2.30
    榦
    2.19
     ''
    2.19
    engkapnya
    2.16
    i
    2.09
     '
    2.05
    Activations Density 0.002%

    No Known Activations