© 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. 12988
    Prev
    Next
    INDEX
    Explanations

    quantified probabilities or proportions

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

    The neuron fires on numeric tokens—especially statistical figures, counts, percentages, and decimal values—i.e. quantitative data 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
     многи
    1.08
    many
    0.90
     muitas
    0.90
     অনেকগুলি
    0.86
     многим
    0.85
     অনেক
    0.83
     많
    0.82
     muchas
    0.82
     mnoh
    0.81
     many
    0.80
    POSITIVE LOGITS
     faktisk
    0.80
     réellement
    0.75
     собственно
    0.68
     '.';
    0.64
     actually
    0.64
     outright
    0.64
     đi
    0.63
    実際に
    0.63
    今回の
    0.63
     tatsächlich
    0.61
    Activations Density 0.311%

    No Known Activations