© 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. 22-GEMMASCOPE-RES-131K
    7. 26542
    Prev
    Next
    INDEX
    Explanations

    temporary or transient

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

    The main thing this neuron does is find numeric literals or number tokens in code and text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ক্ষ
    -0.78
    Heading
    -0.75
    ⋂
    -0.73
    ῥ
    -0.72
    DELAY
    -0.72
    reject
    -0.71
     textil
    -0.71
    Reject
    -0.70
     ガス
    -0.70
     Proc
    -0.69
    POSITIVE LOGITS
     temporary
    1.67
     temporarily
    1.60
     Temporary
    1.41
     tijde
    1.38
    temporary
    1.38
    Temporary
    1.34
    PORARY
    1.16
     transient
    1.13
     momentarily
    1.11
    临时
    1.09
    Activations Density 0.143%

    No Known Activations