© 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. 1689
    Prev
    Next
    INDEX
    Explanations

    historical figures or groups

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

    The neuron fires on nouns naming people or groups of people (e.g. monk, soldier, nuns, Vikings, cave men).

    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
    </h2>
    -1.51
    También
    -1.35
     realmente
    -1.27
     superbes
    -1.19
     estrellas
    -1.19
    şik
    -1.18
     longterm
    -1.18
    龊
    -1.18
    www
    -1.17
     commencé
    -1.17
    POSITIVE LOGITS
     who
    1.58
    </i>
    1.43
    欉
    1.40
    _
    1.38
     from
    1.36
     primit
    1.34
     found
    1.32
     here
    1.32
    on
    1.25
     bassi
    1.24
    Activations Density 0.086%

    No Known Activations