© 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. 34-GEMMASCOPE-RES-131K
    7. 108349
    Prev
    Next
    INDEX
    Explanations

    words starting with lem

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

    The neuron consistently fires on the specific letter sequence “Lem” (i.e. tokens containing “Lem”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    combo
    -0.77
     zoll
    -0.76
    組合
    -0.75
    combs
    -0.74
    文獻
    -0.73
     combination
    -0.73
    ⠝
    -0.73
    ומ
    -0.73
     unreasonable
    -0.71
     advanced
    -0.71
    POSITIVE LOGITS
     Lem
    1.39
    Lem
    1.39
    lem
    1.21
     LEM
    1.18
     lemme
    0.99
    🍋
    0.98
    лем
    0.92
     lemons
    0.88
     Lemma
    0.87
     zest
    0.86
    Activations Density 0.008%

    No Known Activations