© 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. 8794
    Prev
    Next
    INDEX
    Explanations

    lib or library names

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

    This neuron detects tokens containing the substring “lib.”

    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
     порт
    0.66
     رياض
    0.59
     prune
    0.59
    த்துறை
    0.59
    즌
    0.58
    拇
    0.55
     राकेश
    0.55
    ौ
    0.55
     Марафон
    0.54
     Appropri
    0.54
    POSITIVE LOGITS
    ERTY
    0.56
     lib
    0.53
     Lib
    0.51
     हवाई
    0.51
     capped
    0.50
    olt
    0.50
    Liber
    0.49
     Liber
    0.49
    bef
    0.49
    実際の
    0.49
    Activations Density 0.126%

    No Known Activations