© 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. 65911
    Prev
    Next
    INDEX
    Explanations

    bolts, lightning, storm

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

    The neuron responds strongly to phrases describing an organism’s ability to infect warm-blooded animals (including humans).

    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
     scap
    -0.73
     MAF
    -0.71
    渕
    -0.69
    remel
    -0.67
    リの
    -0.66
     προ
    -0.66
     الذ
    -0.66
    驸
    -0.65
     куби
    -0.65
    ライス
    -0.64
    POSITIVE LOGITS
     bolts
    0.98
     Bolt
    0.97
    bolt
    0.96
     trident
    0.94
     lightning
    0.91
     Lightning
    0.90
     bolt
    0.87
     Trident
    0.87
    电机
    0.87
     storm
    0.86
    Activations Density 0.009%

    No Known Activations