© 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. 34-GEMMASCOPE-RES-131K
    7. 63642
    Prev
    Next
    INDEX
    Explanations

    names starting with 'K' or 'Phu'

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

    The neuron fires strongly on tokens that are parts of personal proper names (e.g. surname segments).

    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
    довал
    -0.77
     thankfully
    -0.77
     Pá
    -0.74
    ㎢
    -0.70
    Thankfully
    -0.69
    毂
    -0.69
     kentang
    -0.68
    ilat
    -0.68
     براي
    -0.66
    จะมี
    -0.65
    POSITIVE LOGITS
    ਆਂ
    0.82
     COU
    0.81
     rRNA
    0.79
    deleted
    0.75
     menudo
    0.74
     기
    0.74
    产生的
    0.74
     microbes
    0.73
    ětí
    0.73
    แนว
    0.73
    Activations Density 0.044%

    No Known Activations