© 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. 10979
    Prev
    Next
    INDEX
    Explanations

    `number` `verbs` `years` `times`

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

    The neuron is essentially spotting paragraph or section boundaries by firing strongly on the first salient content word of each new block.

    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
     Ron
    0.79
    n
    0.76
     W
    0.75
     C
    0.72
     GC
    0.70
     A
    0.70
     U
    0.70
     Eton
    0.70
     G
    0.70
     switches
    0.70
    POSITIVE LOGITS
     molécules
    1.05
     révol
    0.95
     Çalış
    0.91
    iré
    0.89
     caractères
    0.88
    Cuál
    0.88
    ïdes
    0.87
     protéines
    0.86
     prestazioni
    0.85
    Aquí
    0.85
    Activations Density 0.000%

    No Known Activations