© 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. 119197
    Prev
    Next
    INDEX
    Explanations

    darkness and night

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

    The neuron fires on mentions of darkness or “dark” themes—i.e. words referring to darkness, a dark environment, or the concept of being in the dark.

    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
    oriya
    -0.85
    (?)
    -0.85
    (!)
    -0.84
    ึ้น
    -0.83
     zeigte
    -0.82
    Lato
    -0.81
    Lazar
    -0.80
     архи
    -0.79
     Traum
    -0.78
    ceras
    -0.77
    POSITIVE LOGITS
     night
    1.07
     shrou
    0.92
     夜
    0.91
     shroud
    0.91
     black
    0.91
    🕛
    0.88
     turysty
    0.88
     оку
    0.87
     ночи
    0.86
     Night
    0.85
    Activations Density 0.029%

    No Known Activations