© 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. 84520
    Prev
    Next
    INDEX
    Explanations

    boron and its compounds

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

    chemical elements and compounds, particularly those containing boron.

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

    This neuron fires on document structural markers—like section or heading labels (e.g. numbered or titled headers) in technical, legal, or code texts.

    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
    FIX
    -0.79
    stylish
    -0.73
    適合
    -0.71
    gitter
    -0.68
    gráficas
    -0.68
     चाहते
    -0.67
    artikel
    -0.65
     Valuable
    -0.65
    ougars
    -0.64
    Identific
    -0.64
    POSITIVE LOGITS
     boron
    1.84
     Boron
    1.58
    Boron
    1.36
    bor
    1.30
     Bor
    1.26
     bor
    1.25
    硼
    1.15
     бор
    1.11
     Бор
    1.04
    Bor
    1.02
    Activations Density 0.054%

    No Known Activations