© 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. 105460
    Prev
    Next
    INDEX
    Explanations

    public followed by noun

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

    The main thing this neuron does is detect occurrences of the word “public.”

    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
    </em>
    -1.91
     aprob
    -1.64
    翃
    -1.63
    蓠
    -1.61
    XXV
    -1.48
      
    -1.47
    莘
    -1.45
     posibles
    -1.45
     are
    -1.43
    getConfiguration
    -1.43
    POSITIVE LOGITS
    From
    1.57
    Many
    1.51
     rajut
    1.48
    Our
    1.47
     istimewa
    1.46
     kılıf
    1.44
     transparan
    1.43
     refuerzo
    1.41
     noires
    1.39
    e
    1.39
    Activations Density 0.039%

    No Known Activations