© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8448
    Prev
    Next
    INDEX
    Explanations

    fraud detection

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

    The neuron activates on numeric tokens or quantity indicators (e.g. numbers and measurement units).

    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
     mismas
    0.63
    なども
    0.61
     및
    0.57
    作為
    0.54
    cds
    0.54
    緎
    0.54
     एवं
    0.54
     moieties
    0.53
    ༈
    0.53
     illetve
    0.53
    POSITIVE LOGITS
    赶紧
    0.63
     rapidement
    0.57
     plötzlich
    0.56
    女友
    0.55
     rapidamente
    0.54
     внима
    0.54
     girlfriend
    0.54
     szybko
    0.53
     unknowingly
    0.53
     Boyfriend
    0.53
    Activations Density 0.036%

    No Known Activations