© 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. 3762
    Prev
    Next
    INDEX
    Explanations

    freely available and distributable

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

    The neuron strongly activates on occurrences of the word "freely."

    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
     \
    -3.08
    ar
    -2.95
    ↵↵
    -2.92
     “
    -2.80
     a
    -2.67
     &
    -2.64
                                   
    -2.55
     We
    -2.53
     wesentlichen
    -2.38
      
    -2.34
    POSITIVE LOGITS
    When
    2.84
    鹮
    2.64
    Without
    2.61
    Despite
    2.59
    While
    2.55
    there
    2.53
    ."
    2.50
    There
    2.47
    Even
    2.47
    Because
    2.39
    Activations Density 0.002%

    No Known Activations