© 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. 41971
    Prev
    Next
    INDEX
    Explanations

    start of sentence

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

    The neuron is picking out numeric measurements and quantitative details—distances, durations, sizes, quantities, and their associated units.

    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
     utafiti
    -1.63
     Outros
    -1.58
     datter
    -1.56
     Autres
    -1.54
     Paroles
    -1.52
     saken
    -1.52
     Muito
    -1.50
     hals
    -1.48
     jual
    -1.48
     barnet
    -1.48
    POSITIVE LOGITS
     will
    1.70
     -
    1.59
    atasaray
    1.53
    ':
    1.48
    有事
    1.44
    --)
    1.41
    管家
    1.41
    ha
    1.34
    VideoCapture
    1.33
    geſ
    1.32
    Activations Density 0.013%

    No Known Activations