© 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. 12524
    Prev
    Next
    INDEX
    Explanations

    other's

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

    The neuron flags references to other people or individuals (e.g., “other,” “others,” “people,” “executives”).

    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
    ary
    0.77
     every
    0.71
    ATIVE
    0.71
     eldest
    0.70
     other
    0.70
    ごとに
    0.70
    ﺎ
    0.70
    ￣
    0.69
    atore
    0.69
    lio
    0.68
    POSITIVE LOGITS
     niż
    1.18
     than
    1.08
     similarly
    1.05
    worldly
    1.02
     decât
    0.99
     Than
    0.90
     비슷한
    0.89
     semelhantes
    0.88
     similar
    0.87
     simili
    0.86
    Activations Density 0.259%

    No Known Activations