© 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. 2141
    Prev
    Next
    INDEX
    Explanations

    address components

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

    The neuron fires on numeric tokens—especially sequences of digits (including decimals) in addresses or identifiers.

    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
    원본
    0.55
     পররাষ্ট্র
    0.55
    Istituto
    0.55
    분
    0.55
    원이
    0.54
     최대
    0.53
    ApiCalls
    0.52
     Istituto
    0.52
    𝐈
    0.52
    мит
    0.52
    POSITIVE LOGITS
     campus
    0.66
     quartiers
    0.65
     building
    0.64
     कैंपस
    0.63
     road
    0.62
     streets
    0.59
     overlooking
    0.59
     street
    0.57
     postal
    0.57
     room
    0.56
    Activations Density 0.048%

    No Known Activations