© 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. 6313
    Prev
    Next
    INDEX
    Explanations

    definition of

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

    The neuron is primarily triggered by commas (punctuation separators).

    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
    з
    0.81
    ટું
    0.70
    ้ง
    0.64
    化物
    0.64
    че
    0.64
    ול
    0.63
    зву
    0.63
    등
    0.62
    iscono
    0.61
    ר
    0.61
    POSITIVE LOGITS
     toda
    1.02
     arka
    0.94
     tejto
    0.89
     Preto
    0.88
     vrata
    0.87
     alemão
    0.86
     pemilihan
    0.86
    y
    0.85
     allerede
    0.84
     homenaje
    0.84
    Activations Density 0.011%

    No Known Activations