© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71310
    Prev
    Next
    INDEX
    Explanations

    famous and named things

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

    The neuron fires on adjectives and descriptors that highlight prominence or notability—words like “scenic,” “famous,” “popular,” or “spot” in landmark descriptions.

    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
    {
    -1.76
     aislados
    -1.66
    people
    -1.63
     $
    -1.59
     cerrados
    -1.55
    蹑
    -1.53
     romanos
    -1.49
     larga
    -1.48
     its
    -1.48
     americanos
    -1.45
    POSITIVE LOGITS
     شدند
    1.90
     from
    1.65
    鄚
    1.58
    啬
    1.55
     absence
    1.55
    liel
    1.45
     بداية
    1.44
    麪
    1.43
    豨
    1.41
    辮
    1.39
    Activations Density 0.007%

    No Known Activations