© 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. 4206
    Prev
    Next
    INDEX
    Explanations

    company hosting and prices

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

    The neuron is strongly triggered by the word “two,” i.e. references to pairs or dual connections.

    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
    ana
    0.89
    на
    0.84
    ל
    0.82
    ко
    0.80
    نا
    0.79
    ব
    0.79
    ز
    0.78
    ve
    0.77
    ند
    0.77
    фор
    0.75
    POSITIVE LOGITS
    电器
    0.79
     ontv
    0.75
     события
    0.73
    后果
    0.73
     hre
    0.73
     рэгістрацыі
    0.73
     rewire
    0.71
    ләү
    0.70
     куда
    0.70
     cep
    0.69
    Activations Density 0.001%

    No Known Activations