© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 3150
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens containing a decimal point (floating‐point 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
     as
    1.25
     is
    1.20
     in
    1.20
     to
    1.18
    .
    1.18
    ,
    1.17
     Colombeau
    1.15
     and
    1.11
     for
    1.08
     Haunted
    1.07
    POSITIVE LOGITS
     വിവിധ
    1.18
    <unused985>
    1.14
    <unused1061>
    1.14
    竰
    1.08
    ॕ
    1.07
    <unused1068>
    1.05
    <unused682>
    1.05
    羵
    1.04
    堈
    1.03
    <unused434>
    1.03
    Activations Density 0.000%

    No Known Activations