© 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. 105252
    Prev
    Next
    INDEX
    Explanations

    identifying word roots and predicting suffixes

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

    the word "indistinguishable" and closely related variants like "distinguishable" or words with the root "distinguish".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly activates on the term “indistinguishable” (and its morphological components).

    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
    O
    -3.41
      
    -3.13
     –
    -3.09
     \
    -3.09
    ”
    -2.97
    —
    -2.86
    <em>
    -2.81
          
    -2.81
                 
    -2.80
    POSITIVE LOGITS
     omdat
    2.86
     fortalec
    2.52
     ventilador
    2.47
    NÍ
    2.39
     vlasy
    2.34
     lavado
    2.33
    afbeelding
    2.33
    힣
    2.31
     consentimiento
    2.30
     ochran
    2.28
    Activations Density 0.001%

    No Known Activations