© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110449
    Prev
    Next
    INDEX
    Explanations

    compound or substance followed by a descriptor

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

    The neuron activates for the word "Compound" or "substance" in scientific and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     !!!!!
    -1.05
     WAIT
    -1.03
    션
    -0.96
     останов
    -0.95
     delapan
    -0.93
     якості
    -0.93
     ê
    -0.92
     garante
    -0.92
     magnitude
    -0.90
    ColElement
    -0.90
    POSITIVE LOGITS
    ~」
    1.06
     Substance
    0.97
    Substance
    0.96
    mathcal
    0.91
     cây
    0.88
     Substanz
    0.86
     their
    0.86
    their
    0.85
    ام
    0.84
     enable
    0.84
    Activations Density 0.024%

    No Known Activations