© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12549
    Prev
    Next
    INDEX
    Explanations

    visa requirements based on nationality

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

    This neuron responds to passages giving software-or computer-related instructions or warnings (e.g. download/uninstall steps, PC optimization, stolen content notices).

    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_31_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
    )。
    0.61
    appeared
    0.53
    ibraries
    0.52
    </td>
    0.51
    列表
    0.51
     Oggi
    0.51
    ようになりました
    0.50
     نیز
    0.49
    ătă
    0.49
     müşter
    0.49
    POSITIVE LOGITS
     REMOTE
    0.59
     remote
    0.56
     noite
    0.56
     go
    0.54
    Remote
    0.54
     circunstancias
    0.52
    䧺
    0.52
     distant
    0.51
    ете
    0.51
     মুক্ত
    0.51
    Activations Density 0.001%

    No Known Activations