© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6937
    Prev
    Next
    INDEX
    Explanations

    atmosphere of fiction

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

    The main thing this neuron does is find numeric expressions—quantities, measurements, and statistics (numbers, counts, dimensions) 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
     stalwart
    0.91
     continually
    0.90
     dogged
    0.90
    lik
    0.89
    i
    0.88
    or
    0.87
    3
    0.87
    ie
    0.87
    and
    0.86
    ही
    0.86
    POSITIVE LOGITS
     touristic
    1.70
     Nowadays
    1.59
     advices
    1.46
     significative
    1.41
     minimalistic
    1.37
     parametrization
    1.37
     adimensional
    1.36
     nowadays
    1.35
     middlewares
    1.34
    Nowadays
    1.34
    Activations Density 3.289%

    No Known Activations