© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106825
    Prev
    Next
    INDEX
    Explanations

    shipwrecks, salvage, and artefacts

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

    The neuron is keyed to the word “ship.”

    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
    gsSP
    -0.84
    Insn
    -0.81
     upgra
    -0.81
     樹
    -0.77
    Зноскі
    -0.76
    меется
    -0.75
    autom
    -0.74
    umacher
    -0.74
    삽
    -0.73
     reforma
    -0.73
    POSITIVE LOGITS
     wreck
    1.69
     salvage
    1.64
     treasure
    1.28
    wreck
    1.23
     wrecks
    1.19
     salv
    1.18
     Wreck
    1.18
     underwater
    1.17
     wreckage
    1.16
     Salvage
    1.16
    Activations Density 0.040%

    No Known Activations