© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90605
    Prev
    Next
    INDEX
    Explanations

    names and prefixes

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

    The neuron fires strongly on the character sequence “indis” wherever it appears inside words.

    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
    ’
    -3.97
    s
    -3.84
    a
    -3.77
    2
    -2.77
    1
    -2.66
    ༵
    -2.64
    4
    -2.64
     lesquelles
    -2.58
    "
    -2.53
    3
    -2.50
    POSITIVE LOGITS
    韞
    3.02
    )}]{
    2.59
     に関する
    2.55
    ⁍
    2.50
     renovables
    2.47
    焌
    2.45
     competitivos
    2.44
     damaging
    2.44
    lardan
    2.41
    rogels
    2.38
    Activations Density 0.020%

    No Known Activations