© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1202
    Prev
    Next
    INDEX
    Explanations

    scientific preparation and procedures

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

    section headers and methodology parts in scientific papers.

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

    This neuron fires on numeric tokens—section or subsection numbers, years, reference numbers, and other standalone figures.

    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
     desde
    -0.90
     another
    -0.88
     Result
    -0.87
     vs
    -0.86
    Result
    -0.83
    叔
    -0.82
     when
    -0.79
    }*
    -0.79
     Conclusion
    -0.79
    thenReturn
    -0.78
    POSITIVE LOGITS
     preparation
    1.86
     chemicals
    1.52
     procedure
    1.41
    Preparation
    1.35
     Chemicals
    1.29
     Preparation
    1.25
     procedures
    1.23
     equipment
    1.18
     animals
    1.13
    Chemicals
    1.13
    Activations Density 0.042%

    No Known Activations