© 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. 55839
    Prev
    Next
    INDEX
    Explanations

    words related to nominate or nominal

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

    This neuron responds to occurrences of the character sequence “nom” (as in nominal, nominee, anomalous, nominated).

    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
    nós
    -0.86
    booster
    -0.85
    開店
    -0.79
     obstacles
    -0.79
    بوط
    -0.78
    فرم
    -0.75
     Bang
    -0.73
    ölcs
    -0.73
    Rachael
    -0.73
     broadly
    -0.73
    POSITIVE LOGITS
    Nom
    1.34
     NOM
    1.27
    nom
    1.24
     Nom
    1.18
     nom
    1.11
    NOM
    1.09
     Nomin
    0.99
    Nomin
    0.99
     nomin
    0.96
     konz
    0.86
    Activations Density 0.016%

    No Known Activations