© 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. 2932
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of data‐security and privacy safeguards (e.g. “electronic,” “confidentiality,” “security measures,” 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_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
    ／
    0.70
    様専用
    0.68
     sebagainya
    0.67
    DataGridView
    0.65
    cellaneous
    0.64
    /
    0.64
    FileType
    0.63
    மானிய
    0.62
    itories
    0.61
    %@",
    0.61
    POSITIVE LOGITS
    时间和
    0.71
     اتارنا
    0.70
     illetve
    0.68
    中期
    0.68
     Messrs
    0.66
     როგორც
    0.65
     Jé
    0.63
     ehrlich
    0.61
     hoping
    0.61
     লেখা
    0.60
    Activations Density 0.397%

    No Known Activations