© 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. 3726
    Prev
    Next
    INDEX
    Explanations

    g

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

    The neuron strongly fires on tokens containing numbers or numeric expressions (years, measurements, prices, URLs with digits, etc.).

    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
     ("[
    1.02
     amacıyla
    0.94
     gerçekleştir
    0.91
     unambiguously
    0.89
     conformément
    0.89
     implementación
    0.88
     nhằm
    0.86
     ดังนั้น
    0.84
     unwavering
    0.81
     efficacement
    0.81
    POSITIVE LOGITS
    名字
    1.16
     नही
    1.08
     name
    1.04
    刋
    1.03
     हमको
    1.02
    好像
    1.02
     negroes
    1.01
     yrs
    1.00
     nomes
    1.00
    と言う
    0.99
    Activations Density 0.040%

    No Known Activations