© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1498
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting numerical values expressed with decimal points.

    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_24_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
    时间和
    0.51
     automó
    0.49
     interno
    0.48
    のですが
    0.47
    ції
    0.46
    1
    0.46
     rango
    0.46
     dasar
    0.45
     tetapi
    0.44
     nomenclature
    0.44
    POSITIVE LOGITS
     sebagainya
    0.75
    อื่นๆ
    0.63
    ⟥
    0.57
     म्हणूनच
    0.57
    ContentType
    0.57
     whatnot
    0.55
    쫀득
    0.54
    REAT
    0.54
     अगदी
    0.54
    StarGo
    0.53
    Activations Density 0.014%

    No Known Activations