© 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. 10-GEMMASCOPE-RES-131K
    7. 124160
    Prev
    Next
    INDEX
    Explanations

    Ferdinand, adipose tissue

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

    The name "Ferdinand" in various contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron selectively activates on occurrences of the proper name “Ferdinand.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     \
    -2.89
     been
    -2.86
    咴
    -2.72
    梣
    -2.70
    and
    -2.67
    k
    -2.64
    or
    -2.52
    ."
    -2.48
    ）：
    -2.48
    蓴
    -2.47
    POSITIVE LOGITS
     ocultar
    2.77
     distinguir
    2.61
     dijeron
    2.56
     comienzan
    2.56
     Während
    2.55
     revisar
    2.50
     optimizar
    2.48
     averiguar
    2.48
     mirando
    2.47
     valorar
    2.47
    Activations Density 0.003%

    No Known Activations