© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9701
    Prev
    Next
    INDEX
    Explanations

    again, happy to explain

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

    The neuron is triggered by citation page‐number markers (e.g. the “pp” token before page ranges) in bibliographic references.

    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
    楸
    0.86
    letzt
    0.81
    朲
    0.76
    ic
    0.76
    ärk
    0.73
    invalid
    0.70
    เศษ
    0.70
    朶
    0.70
    λά
    0.69
     ара
    0.68
    POSITIVE LOGITS
     両
    0.83
     snork
    0.82
     synergies
    0.81
     perforation
    0.79
     Baton
    0.78
     wounding
    0.75
     decommissioning
    0.75
     loadAnimation
    0.75
     Bats
    0.75
    ”?
    0.74
    Activations Density 0.001%

    No Known Activations