© 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. 6416
    Prev
    Next
    INDEX
    Explanations

    keen, end, zen

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

    The neuron strongly activates on personal names (especially author surnames) in academic‐style citations.

    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
    ্ট
    0.70
    莯
    0.66
     destroy
    0.65
    тів
    0.62
    ѣ
    0.60
    subdir
    0.60
    ल्ल्या
    0.59
     ​​​​
    0.59
     fairly
    0.59
     Biggest
    0.59
    POSITIVE LOGITS
    vironment
    0.89
    mity
    0.86
    sores
    0.79
    chyma
    0.79
    kel
    0.74
    riques
    0.74
    bergs
    0.73
    forcement
    0.73
    berger
    0.72
    bosch
    0.72
    Activations Density 0.899%

    No Known Activations