© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104299
    Prev
    Next
    INDEX
    Explanations

    whole, entire, overall before noun

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

    The neuron detects words expressing totality or completeness, such as “whole” and “entire.”

    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
     Перейти
    -1.68
    </i>
    -1.62
     sorpresas
    -1.50
     Familienname
    -1.50
     見える
    -1.47
    觊
    -1.45
     recibe
    -1.45
     in
    -1.44
     Betrachtung
    -1.44
    Formik
    -1.43
    POSITIVE LOGITS
    嗶
    1.71
    および
    1.71
     –
    1.63
    徧
    1.58
    neling
    1.54
     marea
    1.54
    诹
    1.50
    缐
    1.47
    MenuInflater
    1.46
    which
    1.45
    Activations Density 0.002%

    No Known Activations