© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 64671
    Prev
    Next
    INDEX
    Explanations

    protein functions or types

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

    This neuron detects biochemical and protein-related terminology, particularly focusing on protein names, molecular structures, and biochemical compounds.

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

    The neuron is especially sensitive to technical biochemical terms, most strongly flagging occurrences of “binding” and related protein‐binding phrases.

    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
    เอ
    -0.80
     PTE
    -0.73
     Kementerian
    -0.72
    Happiness
    -0.71
     Departamento
    -0.70
    ностью
    -0.70
    Weekend
    -0.70
    ställ
    -0.68
    pegno
    -0.67
    ưỡi
    -0.67
    POSITIVE LOGITS
     annex
    1.02
     binding
    0.95
    coding
    0.93
     acidic
    0.91
     Binding
    0.86
    WAP
    0.85
    aller
    0.84
    spots
    0.83
     allergen
    0.81
     protein
    0.80
    Activations Density 0.287%

    No Known Activations