© 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. 102192
    Prev
    Next
    INDEX
    Explanations

    human primates

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

    references to humans, particularly non-human primates, scientific subjects, and political or organizational entities.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on mentions of “non-human” (i.e. when the text refers to non-human subjects).

    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
     that
    -2.06
    macam
    -1.55
    ಱ
    -1.48
    </strong>
    -1.45
     betek
    -1.38
    those
    -1.36
     Reſ
    -1.35
     intende
    -1.35
     solución
    -1.34
     ubicación
    -1.34
    POSITIVE LOGITS
            
    1.65
     Recently
    1.58
     tentang
    1.57
     Even
    1.50
     että
    1.48
    nienia
    1.48
    ↵
    1.48
     ketika
    1.47
     Almost
    1.47
     But
    1.45
    Activations Density 0.092%

    No Known Activations