© 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. 10-GEMMASCOPE-RES-131K
    7. 59972
    Prev
    Next
    INDEX
    Explanations

    treasure trove, hunt, chest

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

    The neuron fires on mentions of “treasure” or “trove,” flagging references to valuable collections or discoveries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鲧
    -2.42
    鰨
    -2.20
    很棒
    -2.19
    uttgart
    -2.19
    谂
    -2.17
    鶺
    -2.14
    漚
    -2.11
    ⎚
    -2.09
     invitación
    -2.08
    sizeCache
    -2.06
    POSITIVE LOGITS
     
    3.52
    {
    2.66
    <bos>
    2.61
    鴣
    2.08
     of
    2.06
     

    1.90
     trove
    1.86
     —
    1.82
     is
    1.78
     worin
    1.78
    Activations Density 0.005%

    No Known Activations