© 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. 34-GEMMASCOPE-RES-131K
    7. 58834
    Prev
    Next
    INDEX
    Explanations

    named entities and classifications

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

    The neuron specializes in spotting “by”-style attributions and the proper names (people, teams, labs, surveys, observatories) that follow them.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    日至
    -0.82
     guerrero
    -0.73
     Sald
    -0.71
     SPECT
    -0.71
    Cantidad
    -0.70
     acu
    -0.69
    ceau
    -0.69
    ឈ
    -0.69
    PWD
    -0.68
    味は
    -0.68
    POSITIVE LOGITS
     descobri
    0.90
     découvrir
    0.90
     team
    0.89
    discover
    0.89
    lateur
    0.87
    Deep
    0.86
     découver
    0.85
    initiative
    0.82
     monoxide
    0.82
    OwnProperty
    0.81
    Activations Density 0.007%

    No Known Activations