© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20652
    Prev
    Next
    INDEX
    Explanations

    plu- followed by dictionary words

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

    This neuron activates on occurrences of the character sequence “plu” (e.g. in words like pluripotent, pluperfect, Pluridis).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蹰
    -3.00
    踽
    -2.91
    ↵↵
    -2.89
    箆
    -2.86
    噚
    -2.64
    鏝
    -2.56
     falle
    -2.48
    嗵
    -2.45
     Atención
    -2.36
    ꦱ
    -2.34
    POSITIVE LOGITS
     "
    2.77
    which
    2.73
     -
    2.52
    Several
    2.45
    ."
    2.45
     theres
    2.45
    Alongside
    2.41
    ではでは
    2.38
     WHICH
    2.38
    -"
    2.38
    Activations Density 0.009%

    No Known Activations