© 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. 10-GEMMASCOPE-RES-131K
    4. 1838
    Prev
    Next
    INDEX
    Explanations

    Nuclear medicine, Chiropractor

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

    HTML/code special characters, particularly ampersands (&) and semicolons (;) in markup and comments.

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

    This neuron responds to HTML character‐entity references (e.g. “ ,” “",” numeric entities, etc.).

    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
    0
    -2.59
    1
    -2.56
    2
    -2.36
    7
    -2.27
    3
    -2.19
    龗
    -2.08
     Songtext
    -2.06
    9
    -2.00
    6
    -1.94
     proveniente
    -1.86
    POSITIVE LOGITS
    )))),
    2.09
    );*/
    1.97
    h
    1.83
    m
    1.80
     kekasih
    1.80
    éreo
    1.80
     tampaknya
    1.80
     blir
    1.78
    g
    1.76
     была
    1.74
    Activations Density 0.001%

    No Known Activations