© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60127
    Prev
    Next
    INDEX
    Explanations

    asp.net and aspiration

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

    The neuron strongly activates on occurrences of “asp” (in any case) and related token fragments (e.g. “Asp,” “asp.net”), so it’s detecting mentions of the ASP/ASP.NET term.

    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
    Walking
    -0.74
     albic
    -0.71
    Laura
    -0.70
     sinners
    -0.70
    );
    -0.70
     輪
    -0.69
    無人
    -0.69
    UG
    -0.69
    য়ে
    -0.69
    Walk
    -0.69
    POSITIVE LOGITS
     Asp
    1.41
    Asp
    1.21
     asp
    1.14
     Aspir
    1.02
     aspirations
    0.97
    aspir
    0.94
    Aspiration
    0.93
    asp
    0.93
     ASP
    0.90
    铰
    0.87
    Activations Density 0.025%

    No Known Activations