© 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. 77570
    Prev
    Next
    INDEX
    Explanations

    words starting with L

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

    The neuron is primarily activated by tokens beginning with the letters “La.”

    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
    知識
    -0.84
    כם
    -0.81
    工厂
    -0.80
     wykonania
    -0.79
     campana
    -0.79
    燜
    -0.79
    …！
    -0.78
    時間は
    -0.78
    って思
    -0.78
     considerations
    -0.76
    POSITIVE LOGITS
     Ла
    0.95
     Lag
    0.94
    owę
    0.89
     Lakers
    0.88
     Lamb
    0.86
     LAMB
    0.85
     LAM
    0.85
     Larsson
    0.85
    laren
    0.84
     Larry
    0.83
    Activations Density 0.023%

    No Known Activations