© 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. 35017
    Prev
    Next
    INDEX
    Explanations

    esecuzione, Fisica, Éxitos, ex vivo, esecuzione, EXAMPLE

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

    This neuron activates on subword pieces characteristic of Romance‐language words (e.g. Italian/Spanish roots and accents).

    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
     reporting
    -0.93
    formerly
    -0.91
     report
    -0.88
     CURRENT
    -0.84
    yna
    -0.83
     engineer
    -0.83
     گو
    -0.82
    ressing
    -0.82
    ong
    -0.81
    reports
    -0.81
    POSITIVE LOGITS
     dispensation
    0.82
     Ultimately
    0.81
    Patrol
    0.77
     Aún
    0.77
     ousted
    0.77
     inexperienced
    0.77
     eliminating
    0.75
     hibernation
    0.74
     Being
    0.74
     fruition
    0.73
    Activations Density 0.010%

    No Known Activations