© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38043
    Prev
    Next
    INDEX
    Explanations

    lithium-ion, iron, surgical, fatal

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

    chemical compounds and elements in scientific research papers, particularly related to battery technology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron primarily detects scientific numeric expressions and chemical‐formula tokens (e.g. digits, units, and molecular formulas).

    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
     Judah
    -0.72
    wl
    -0.71
    悲しい
    -0.71
    ستین
    -0.71
     HAC
    -0.68
     Burn
    -0.68
    marginLeft
    -0.67
    Wl
    -0.67
     Son
    -0.66
     Bern
    -0.66
    POSITIVE LOGITS
     cathode
    1.39
    Iron
    0.91
     iron
    0.82
     olives
    0.81
    iron
    0.79
     preuß
    0.78
     phosphates
    0.77
    ="_
    0.76
    ارض
    0.76
     cobalt
    0.75
    Activations Density 0.046%

    No Known Activations