© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8177
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets

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

    The neuron strongly activates on numeric tokens in reference entries—especially four-digit years or decimal page/volume numbers in 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
     clearInterval
    0.70
     }*/
    0.67
    ()}
    0.65
    *}
    0.62
    }]
    0.62
     EventEmitter
    0.61
    })();
    0.60
    ാരണ
    0.60
    }*/
    0.59
     setIsLoading
    0.59
    POSITIVE LOGITS
    )=
    0.61
    )/
    0.59
    apk
    0.56
    azen
    0.56
     येते
    0.56
    )/(
    0.55
    )
    0.54
    )\
    0.52
    iad
    0.52
     फ्रंट
    0.52
    Activations Density 0.000%

    No Known Activations