© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3391
    Prev
    Next
    INDEX
    Explanations

    Final Answer: The final answer is $\boxed{}$

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

    This neuron fires on commercial call-to-action terms offering immediate access or downloads (e.g. “Instant,” “Download,” “Access”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    </h4>
    0.73
    Related
    0.64
     เรื่อง
    0.63
    Topics
    0.60
     Related
    0.59
    Lecture
    0.59
    Topic
    0.58
    gestion
    0.58
    Woods
    0.57
    淖
    0.57
    POSITIVE LOGITS
     uzys
    0.62
     lapse
    0.62
     glimmer
    0.61
     instant
    0.59
     instantaneous
    0.59
     Instant
    0.58
     transmit
    0.56
     ink
    0.55
     id
    0.55
    ানু
    0.55
    Activations Density 0.006%

    No Known Activations