© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2614
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on uppercase initialisms or acronyms (often in parentheses).

    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
    લ
    0.72
    ニャ
    0.67
    getR
    0.66
    euler
    0.66
    𝐫
    0.66
    ！（
    0.65
    𝐚
    0.63
    нан
    0.63
    Dragging
    0.63
    它的
    0.62
    POSITIVE LOGITS
    )/
    0.93
    ),
    0.86
    )
    0.84
    )_
    0.81
    )),
    0.79
    )-
    0.78
    ))
    0.77
    )—
    0.75
    ),”
    0.73
    ,)
    0.72
    Activations Density 0.065%

    No Known Activations