© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9488
    Prev
    Next
    INDEX
    Explanations

    escape / escaped

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

    The neuron strongly activates on broad generalization terms (especially “everybody”/“everyone”) that refer to all or any people.

    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_24_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
    )$
    0.86
    )>=
    0.77
    Sony
    0.73
    ਿਸ
    0.68
    )))
    0.68
     lightweight
    0.66
    Pilot
    0.66
    ka
    0.65
     Osp
    0.64
     landowner
    0.64
    POSITIVE LOGITS
    р
    0.90
    の中に
    0.87
     principais
    0.84
    सुबह
    0.84
     passos
    0.82
    l
    0.82
    ৯
    0.80
     जिनमें
    0.80
    uintes
    0.79
     Мы
    0.79
    Activations Density 0.004%

    No Known Activations