© 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. 365
    Prev
    Next
    INDEX
    Explanations

    commands, locks, reputation, consent, car, data, address, play

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

    The neuron strongly activates on the final, substantive noun of each answer or paragraph, effectively marking the end‐of‐section content word.

    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
     which
    0.46
    which
    0.44
     (
    0.42
    ports
    0.42
     |
    0.40
    <0x0D>
    0.39
    .
    0.39
     :
    0.38
     ((
    0.37
     WHICH
    0.36
    POSITIVE LOGITS
     dacă
    0.55
     jedynie
    0.55
     după
    0.54
     tikai
    0.53
     לאחר
    0.52
     después
    0.51
    cuando
    0.51
     단순히
    0.51
     όταν
    0.50
     jeśli
    0.50
    Activations Density 0.000%

    No Known Activations