© 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. 86961
    Prev
    Next
    INDEX
    Explanations

    Philippine places and titles

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

    The neuron strongly activates on tokens that are parts of named entities—especially proper names of institutions, places, and people.

    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
    Ὁ
    -0.84
    čko
    -0.82
    itev
    -0.78
    district
    -0.78
    District
    -0.77
     District
    -0.75
    ơi
    -0.74
    arono
    -0.74
     Musik
    -0.73
    Ｄ
    -0.73
    POSITIVE LOGITS
     lucu
    0.87
    herjee
    0.82
     lobbies
    0.78
    rifts
    0.75
    Trailing
    0.74
     thermodynamics
    0.71
    iori
    0.69
     glimpses
    0.69
     интегра
    0.68
     Reserv
    0.68
    Activations Density 0.019%

    No Known Activations