© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1088
    Prev
    Next
    INDEX
    Explanations

    top, upper, or end parts

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

    The neuron is detecting words that mark relative positions or stages (e.g. beginning/early, middle, last/end, top/bottom) in time 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_31_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
     Date
    0.49
    the
    0.47
    输入的
    0.44
     На
    0.43
    名称
    0.43
    ország
    0.43
    全
    0.42
     In
    0.42
     Aynı
    0.42
    pada
    0.41
    POSITIVE LOGITS
     few
    0.84
     portion
    0.75
    few
    0.68
    Few
    0.65
     part
    0.62
     tier
    0.62
     percentile
    0.61
     quartile
    0.61
     часть
    0.61
     poucos
    0.59
    Activations Density 0.408%

    No Known Activations