© 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. 13821
    Prev
    Next
    INDEX
    Explanations

    Saturday morning

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

    The neuron strongly activates on numeric tokens and related punctuation—i.e. it identifies numbers, figures, and tabulated numeric data.

    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
    ad
    0.82
    )
    0.81
    ă
    0.80
    ]
    0.77
    ategoria
    0.75
     lekker
    0.74
     dinâmica
    0.73
    maßen
    0.71
    }$)
    0.71
    িকা
    0.70
    POSITIVE LOGITS
    ξε
    0.89
     刺繍
    0.86
     Geophysical
    0.85
    𝘵
    0.85
    می
    0.79
    В
    0.78
    Γ
    0.78
    院士
    0.76
    ்கலை
    0.76
    塔尔
    0.75
    Activations Density 0.000%

    No Known Activations