© 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. 55602
    Prev
    Next
    INDEX
    Explanations

    treasure trove

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

    This neuron detects words referring to hidden or valuable treasures (e.g. treasure, trove, hoard, buried).

    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
    برج
    -0.81
    ائه
    -0.77
    asts
    -0.76
    ेंगे
    -0.73
     estrés
    -0.73
     Lookup
    -0.73
    ག་
    -0.72
     grey
    -0.72
    Huhu
    -0.72
     elevar
    -0.71
    POSITIVE LOGITS
     treasure
    4.00
     treasures
    3.33
    treasure
    2.81
     Treasure
    2.72
     TREAS
    2.53
    Treasure
    2.52
     riches
    2.27
     trésor
    2.22
     gold
    2.20
     treasury
    2.20
    Activations Density 0.032%

    No Known Activations