© 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. 1680
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on technical identifier tokens—especially uppercase acronyms, environment‐variable names, flags, and other code or shell-command keywords.

    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
    <eos>
    0.85
    ↵↵
    0.69
     ‎
    0.63
    </u>
    0.61
     ®
    0.57
     ‘’
    0.55
     (!)
    0.55
     ™
    0.54
     modest
    0.53
     zei
    0.52
    POSITIVE LOGITS
    .}\
    1.99
    }\
    1.84
    .\
    1.80
    )}\
    1.70
    )\
    1.70
    ()\
    1.68
    。\
    1.68
    ?\
    1.66
    |}\
    1.63
    }}\
    1.60
    Activations Density 0.355%

    No Known Activations