© 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. 10-GEMMASCOPE-RES-131K
    7. 103105
    Prev
    Next
    INDEX
    Explanations

    permeability, permeation

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

    This neuron detects forms of the word "permeate" and related terms like "permeability" or "permeation."

    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_10/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
     Of
    -2.94
     Our
    -2.78
     comienzan
    -2.67
     We
    -2.66
     Meanwhile
    -2.42
    我也不
    -2.38
    一旁
    -2.30
     While
    -2.28
     o
    -2.27
     However
    -2.25
    POSITIVE LOGITS
    the
    3.94
     纹身
    2.81
    鷙
    2.70
    镚
    2.66
    寕
    2.61
    鰱
    2.59
    峮
    2.55
     pesa
    2.53
     Logement
    2.50
    媖
    2.50
    Activations Density 0.025%

    No Known Activations