© 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. 42434
    Prev
    Next
    INDEX
    Explanations

    names starting with G or R

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

    The neuron is triggered by personal names containing the substring “gina” or “gino,” e.g. Gina, Regina, Georgina, Gino, and Geno.

    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
     Which
    -3.36
    、“
    -2.95
     Because
    -2.92
     Its
    -2.89
     Schauspieler
    -2.88
     Faced
    -2.83
     Needless
    -2.81
     dritten
    -2.77
    乆
    -2.73
     Now
    -2.72
    POSITIVE LOGITS
    踯
    2.95
    琑
    2.75
    圌
    2.61
    E
    2.56
     JOB
    2.48
     verborgen
    2.42
     ͡
    2.39
    从来没有
    2.34
    鷽
    2.34
    薷
    2.33
    Activations Density 0.003%

    No Known Activations