© 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. 890
    Prev
    Next
    INDEX
    Explanations

    This neuron detects quantitative geographic or topographic details (measurements, numbers, and related place descriptors).

    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
    0.54
     superhuman
    0.53
     compressed
    0.52
    y
    0.49
     ২৯
    0.49
     k
    0.48
    很难
    0.48
     bukanlah
    0.47
     r
    0.47
     compression
    0.47
    POSITIVE LOGITS
     এবং
    0.85
     wobei
    0.79
     และ
    0.79
    そして
    0.78
     जिसमें
    0.77
    ។
    0.76
    এবং
    0.75
    และ
    0.75
     आणि
    0.74
    했으며
    0.74
    Activations Density 0.083%

    No Known Activations