© 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. 95424
    Prev
    Next
    INDEX
    Explanations

    first names and last names

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

    The neuron fires on isolated single uppercase letters (author initials or similar stand-alone capital tokens).

    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
     resina
    -1.65
     mosca
    -1.64
     frança
    -1.63
     菇
    -1.63
     plafon
    -1.62
     azulejos
    -1.59
     特写
    -1.57
     花纹
    -1.56
     唯美
    -1.54
     mariposa
    -1.52
    POSITIVE LOGITS
    f
    1.88
    j
    1.67
    a
    1.63
    b
    1.63
    p
    1.62
    z
    1.60
    ;
    1.59
    g
    1.57
    n
    1.55
    c
    1.52
    Activations Density 0.023%

    No Known Activations