© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99321
    Prev
    Next
    INDEX
    Explanations

    candle and candlelight

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

    The neuron detects mentions of lighting fixtures or objects (e.g. candles, chandeliers, lamps, and related words).

    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
     Mosk
    -0.92
     alfombra
    -0.88
    ſſion
    -0.86
    beton
    -0.86
     richtig
    -0.83
    sad
    -0.82
     عين
    -0.82
    ÜR
    -0.81
    癇
    -0.79
     procurando
    -0.79
    POSITIVE LOGITS
    abra
    0.98
    holder
    0.96
    ticks
    0.96
    lit
    0.93
    Although
    0.93
    Making
    0.87
    🕯
    0.86
    Many
    0.85
    With
    0.84
    Often
    0.84
    Activations Density 0.009%

    No Known Activations