© 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. 108127
    Prev
    Next
    INDEX
    Explanations

    beta amyloid peptide aggregation

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

    references to amyloid beta peptides associated with Alzheimer's disease and other neurological disorders.

    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
     jud
    -0.76
     Küste
    -0.73
     allowances
    -0.73
     मह
    -0.72
     eingesch
    -0.69
    一台
    -0.69
     dislocations
    -0.68
     blistering
    -0.68
     IPA
    -0.68
     reass
    -0.68
    POSITIVE LOGITS
     peptide
    1.26
     toxicity
    1.08
     aggregation
    1.04
     fragment
    0.99
     peptides
    0.97
     Aggregation
    0.96
     Aggreg
    0.94
     toxic
    0.91
     plaques
    0.88
     plaque
    0.87
    Activations Density 0.137%

    No Known Activations