© 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. 22-GEMMASCOPE-RES-131K
    7. 67691
    Prev
    Next
    INDEX
    Explanations

    noun followed by noun

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

    The neuron fires on the key category or class terms in definitions—i.e. the noun/adjective labels that follow “is a” or the “, a …” appositive in definitional sentences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     _________
    -1.06
     __________
    -1.02
    逕
    -1.01
     insgesamt
    -1.00
     スイッチ
    -1.00
     popoli
    -0.99
    いくつか
    -0.97
    including
    -0.96
    called
    -0.96
     verschiedenen
    -0.95
    POSITIVE LOGITS
     árbol
    1.14
     ännu
    1.12
     panier
    1.09
    สำหรับ
    1.07
     nélk
    1.06
     goles
    1.05
     serveur
    1.04
     kré
    1.04
     autorisation
    1.04
     såg
    1.01
    Activations Density 0.087%

    No Known Activations