© 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. 44602
    Prev
    Next
    INDEX
    Explanations

    immeasurable quantities

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

    The neuron specializes in spotting the word “endless,” i.e. occurrences of that adjective indicating something unbounded or never-ending.

    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
    筇
    -2.73
    ⡦
    -2.61
    鄣
    -2.58
     militare
    -2.48
    孖
    -2.47
    蕷
    -2.45
    鉭
    -2.42
    chopped
    -2.42
     这个
    -2.38
     从
    -2.34
    POSITIVE LOGITS
    ness
    2.97
    鸶
    2.95
    nya
    2.89
    s
    2.81
    an
    2.73
    ～～
    2.58
    zione
    2.45
    no
    2.42
    we
    2.41
    </h3>
    2.39
    Activations Density 0.001%

    No Known Activations