© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3386
    Prev
    Next
    INDEX
    Explanations

    second followed by a specific item

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

    This neuron identifies ordinal indicators (like “second,” “third,” etc.) that mark the sequence of events.

    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
    ü
    1.30
    Storia
    1.09
    ö
    1.05
    י
    1.04
    r
    1.02
    ł
    1.02
    x
    1.00
    ol
    0.99
    Toplam
    0.98
    uar
    0.96
    POSITIVE LOGITS
     installment
    1.08
     baseman
    1.03
     trimester
    1.02
    ምት
    1.01
     deuxième
    0.98
     alarming
    0.97
     instalment
    0.96
     முறையாக
    0.96
     crucifixion
    0.95
     clues
    0.95
    Activations Density 0.038%

    No Known Activations