© 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. 90345
    Prev
    Next
    INDEX
    Explanations

    fate and life's consequences

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

    The neuron strongly activates on broad, abstract “big picture” nouns and concepts—words like world, life, nature, fate, luck, etc.

    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
     violación
    -0.96
     manajemen
    -0.90
     hoppas
    -0.89
     kult
    -0.89
    viez
    -0.87
    bamos
    -0.85
    olalar
    -0.84
    giatan
    -0.84
    glPopMatrix
    -0.83
    Invocation
    -0.82
    POSITIVE LOGITS
     itself
    1.57
     provide
    1.27
     cruel
    1.25
     deliver
    1.19
     gave
    1.16
     decides
    1.15
     kindly
    1.13
     unkind
    1.10
     its
    1.09
     dictates
    1.09
    Activations Density 0.041%

    No Known Activations