© 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. 113675
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or labels

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

    The neuron strongly activates on numeric tokens (integers and decimals), such as counts, measurements, dates, and similar numerical values.

    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
     about
    -1.30
     veio
    -1.30
     know
    -1.29
    ਃ
    -1.28
    etc
    -1.28
     requiere
    -1.28
    再来
    -1.27
     Symptome
    -1.27
    怎样
    -1.26
     next
    -1.24
    POSITIVE LOGITS
    </h1>
    1.64
    </i>
    1.61
     or
    1.49
     zet
    1.38
    ,
    1.37
    Still
    1.34
    –
    1.34
     vallen
    1.29
     stap
    1.27
    pagnole
    1.27
    Activations Density 0.048%

    No Known Activations