© 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. 128060
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric conversion calls in code, especially parseInt (and similar parseFloat or integer‐casting functions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    parsing numbers and integer types

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    I
    -2.30
    :
    -2.19
    -
    -2.19
    /
    -2.08
     &
    -2.05
     :
    -2.03
     in
    -2.02
    At
    -1.96
     T
    -1.95
    -1.93
    POSITIVE LOGITS
    茈
    2.69
    鹇
    2.61
    
    2.56
    秶
    2.31
    雠
    2.31
    肏
    2.30
    
    2.23
    鳚
    2.22
    actéristi
    2.17
    狨
    2.13
    Activations Density 0.000%

    No Known Activations