© 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. 64317
    Prev
    Next
    INDEX
    Explanations

    pond and ponder variations

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

    The neuron fires strongly on any occurrence of the letter sequence “pond” (e.g. in “Pond,” “Ponder,” or “Poundland”).

    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
    骜
    -0.79
     procesamiento
    -0.79
    릅
    -0.77
    ⑅
    -0.77
     trasparente
    -0.77
    rī
    -0.75
     nastro
    -0.75
    Quem
    -0.73
    あって
    -0.73
     Cobalt
    -0.73
    POSITIVE LOGITS
    icher
    1.25
    ponder
    1.09
     ponder
    0.98
     Ponder
    0.90
     scum
    0.84
    oland
    0.77
     pondering
    0.77
    pond
    0.77
     POND
    0.77
    ingress
    0.74
    Activations Density 0.011%

    No Known Activations