© 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. 76657
    Prev
    Next
    INDEX
    Explanations

    water, flame, weather resistance

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

    The neuron flags technical descriptions of material protective properties—especially words indicating resistance or proof (e.g. water-resistant/proof, heat-resistant, flame-retardant).

    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
     Klicken
    -0.91
     Wählen
    -0.90
     citazioni
    -0.87
     of
    -0.79
     सत्यापित
    -0.78
    Здра
    -0.77
     system
    -0.76
    ทั่ว
    -0.76
    ctique
    -0.72
    ogenes
    -0.72
    POSITIVE LOGITS
     resistant
    2.03
     resistance
    1.85
     resisting
    1.70
     resist
    1.49
     Resistance
    1.48
    proof
    1.47
     Resistant
    1.45
     proof
    1.43
    resistant
    1.43
    Proof
    1.33
    Activations Density 0.038%

    No Known Activations