© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7690
    Prev
    Next
    INDEX
    Explanations

    autism spectrum disorder

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

    acronyms related to autism and psychiatric disorders such as ASD (Autism Spectrum Disorder) and PSD (Post-Synaptic Density).

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

    The neuron selectively responds to occurrences of the abbreviation “ASD” (Autism Spectrum Disorder).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ৄ
    -2.92
    咴
    -2.84
    啬
    -2.84
    ቫ
    -2.73
    μος
    -2.69
    镠
    -2.52
    .”
    -2.52
    saison
    -2.50
    
    -2.50
    ቬ
    -2.47
    POSITIVE LOGITS
    но
    2.64
    —
    2.48
    {
    2.48
     It
    2.47
     Coming
    2.39
    糞
    2.28
    と言っても
    2.28
     untuk
    2.27
     Featuring
    2.27
     What
    2.22
    Activations Density 0.004%

    No Known Activations