© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11125
    Prev
    Next
    INDEX
    Explanations

    street addresses, cities, states, zip codes

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

    The neuron selectively activates on multi‐digit numeric sequences—such as dates, times, and street or unit 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
     myCamera
    0.65
     proguardFiles
    0.64
     mangiare
    0.64
     ईमेल
    0.63
    ﺓ
    0.62
     বসিয়
    0.61
     eingerichtet
    0.61
     ὑ
    0.61
     നേരി
    0.61
     scegliere
    0.60
    POSITIVE LOGITS
    -
    0.79
    ph
    0.61
    or
    0.58
    oc
    0.57
    ast
    0.55
     or
    0.54
    eder
    0.54
     ,
    0.54
    ation
    0.52
    ..
    0.52
    Activations Density 0.038%

    No Known Activations