© 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. 374
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric expressions—years, counts, statistics, and other quantitative measurements—in the text.

    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
    。
    0.25
    ().
    0.25
    ).
    0.23
    }.
    0.22
    ('').
    0.22
    `.
    0.21
    ".
    0.21
    }$.
    0.21
     zodat
    0.21
     ).
    0.21
    POSITIVE LOGITS
     there
    0.50
     we
    0.48
    there
    0.41
     they
    0.40
     우리는
    0.39
     আমরা
    0.38
     هناك
    0.37
     आपण
    0.37
     it
    0.36
     हम
    0.35
    Activations Density 2.389%

    No Known Activations