© 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. 83888
    Prev
    Next
    INDEX
    Explanations

    life and purpose

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

    The neuron responds strongly to words referring to life or living (e.g. living, lives, life).

    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
     verstehen
    -0.85
    MatInputModule
    -0.81
     انتظار
    -0.81
    understanding
    -0.81
    detail
    -0.80
     understanding
    -0.77
    MatIconModule
    -0.77
    朦
    -0.76
     forstå
    -0.76
    受験
    -0.76
    POSITIVE LOGITS
     aligned
    1.52
     authentic
    1.43
     align
    1.41
     alignment
    1.30
    ALIGN
    1.24
    aligned
    1.23
    Authentic
    1.21
     alig
    1.20
    Align
    1.20
     aligns
    1.19
    Activations Density 0.027%

    No Known Activations