© 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. 12691
    Prev
    Next
    INDEX
    Explanations

    sequence or stage indicator

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

    The neuron activates on ordinal expressions (e.g. “first,” “second,” “fourth,” “fifth,” etc.) indicating a position or sequence.

    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
     여러
    0.85
     drugih
    0.79
    +](=
    0.72
     často
    0.72
     altri
    0.71
     ఇతర
    0.71
     другие
    0.70
     других
    0.70
     몇
    0.70
     outras
    0.68
    POSITIVE LOGITS
     consecut
    1.15
    这一次
    1.05
     again
    1.02
     Again
    1.01
     iteration
    0.95
     consecutive
    0.95
    번째
    0.95
    Again
    0.94
     installment
    0.93
     AGAIN
    0.92
    Activations Density 0.607%

    No Known Activations