© 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. 1003
    Prev
    Next
    INDEX
    Explanations

    porosity or pores

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

    This neuron detects descriptions of porous materials and their physical properties.

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

    The neuron primarily activates on occurrences of “porous” (and its morphological variants like porosity, porous substrates, porous scaffolds) in technical descriptions.

    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
    玷
    -0.71
     costos
    -0.71
     palais
    -0.71
     muddy
    -0.70
    тесь
    -0.69
    mousedown
    -0.69
    िस्ट
    -0.69
    春节
    -0.67
    toggleClass
    -0.66
     Lawyer
    -0.66
    POSITIVE LOGITS
     foam
    1.41
     porosity
    1.36
     porous
    1.35
     foams
    1.20
     honeycomb
    1.20
     pores
    1.17
     pore
    1.14
     structure
    1.13
    foam
    1.13
     sponge
    1.11
    Activations Density 0.064%

    No Known Activations