© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30547
    Prev
    Next
    INDEX
    Explanations

    music kits

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

    The neuron responds to infrequent or low‐occurrence tokens (i.e. rare subwords or special characters) across the text.

    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
    👈
    -0.89
     checkpoint
    -0.80
     Mom
    -0.80
     convention
    -0.79
    ushort
    -0.78
    сё
    -0.77
    🐛
    -0.77
     commitments
    -0.73
     gaya
    -0.73
     ζωή
    -0.73
    POSITIVE LOGITS
     пузы
    1.00
     bubbles
    0.99
     bubble
    0.94
    bubble
    0.93
     saw
    0.90
     seen
    0.89
     burbuja
    0.85
    escalier
    0.75
     Bubble
    0.75
    erdin
    0.74
    Activations Density 0.029%

    No Known Activations