© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13081
    Prev
    Next
    INDEX
    Explanations

    parents and schools

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

    The neuron primarily activates on the plural noun “parents.”

    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
     their
    -1.22
     Kontakte
    -1.15
     posiblemente
    -1.12
     at
    -1.11
     yaklaşık
    -1.09
    providedIn
    -1.07
     mungkin
    -1.07
     valoraciones
    -1.06
    無事に
    -1.05
     reflexiones
    -1.05
    POSITIVE LOGITS
     conster
    1.29
     applau
    1.23
     ciment
    1.18
     soi
    1.17
     fà
    1.14
     plafon
    1.13
     capot
    1.13
     fuis
    1.13
    two
    1.11
     beton
    1.11
    Activations Density 0.001%

    No Known Activations