© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2257
    Prev
    Next
    INDEX
    Explanations

    react component props or lifecycle

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

    This neuron activates on numeric tokens (e.g. version numbers, decimal values, or other numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]#
    0.66
     libsql
    0.63
    asgi
    0.60
     Arithmetic
    0.58
    🫰
    0.58
    Arithmetic
    0.58
    pgsql
    0.54
     %[
    0.54
     arxivləşdirilib
    0.54
     exception
    0.53
    POSITIVE LOGITS
     componentDid
    1.55
     componentWill
    1.42
     PropTypes
    1.34
     mapStateToProps
    1.20
    ReactDOM
    1.20
    PropTypes
    1.18
     React
    1.15
    React
    1.13
     props
    1.12
    props
    1.09
    Activations Density 0.007%

    No Known Activations