© 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. 1579
    Prev
    Next
    INDEX
    Explanations

    words in other languages

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

    The neuron strongly activates on longer, content‐bearing words (i.e. words of substantial length rather than short function words).

    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
    0.59
    <s>
    0.56
     someone
    0.55
     lightning
    0.55
     leopard
    0.55
     something
    0.54
     trumpet
    0.54
     -*-
    0.54
     anonymous
    0.53
     irresponsible
    0.53
    POSITIVE LOGITS
    ⅽ
    0.80
    喺
    0.75
    靣
    0.71
     kanggo
    0.68
    唔
    0.67
     فِي
    0.65
     উঠিয়া
    0.62
    嘅
    0.62
    僮
    0.62
    寔
    0.62
    Activations Density 0.639%

    No Known Activations