© 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. 66345
    Prev
    Next
    INDEX
    Explanations

    Gold/Silver mining stocks

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

    The neuron fires on mentions of a specialized software tool—specifically a “tool used to extract files from game archives.”

    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
     करे
    -0.96
    chord
    -0.91
     Trock
    -0.86
    числи
    -0.84
     estre
    -0.84
    DbType
    -0.83
    }}}$
    -0.81
     rack
    -0.81
     claro
    -0.77
    に行ってきました
    -0.77
    POSITIVE LOGITS
    Unk
    1.08
     patching
    0.88
     unk
    0.88
     zapal
    0.86
     USF
    0.84
     packers
    0.84
     disassembly
    0.83
     rom
    0.83
     ROM
    0.83
    înt
    0.82
    Activations Density 0.025%

    No Known Activations