© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115965
    Prev
    Next
    INDEX
    Explanations

    Jiu, Kung, Kong, google, regex

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

    This neuron selectively responds to named entities and other uncommon proper nouns or specialized technical terms.

    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
    Фар
    -0.83
    ushes
    -0.73
     cocina
    -0.69
     velocidad
    -0.69
    hooks
    -0.69
    Administrator
    -0.68
    icia
    -0.68
     Gonzales
    -0.68
    Icon
    -0.66
    גם
    -0.66
    POSITIVE LOGITS
    fu
    1.59
    Fu
    1.52
     Fu
    1.52
     fu
    1.51
    FU
    1.26
     FU
    1.21
     Kung
    1.02
     kung
    1.02
    ufu
    0.88
    zman
    0.87
    Activations Density 0.081%

    No Known Activations