© 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. 9554
    Prev
    Next
    INDEX
    Explanations

    DE followed by letters, numbers, or patents

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

    The neuron never activates on any token—it doesn’t detect or respond to any pattern.

    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
    "
    -3.41
    V
    -2.88
    the
    -2.86
    to
    -2.69
    ↵↵
    -2.56
     eds
    -2.48
    柃
    -2.45
     упаковка
    -2.41
     myriad
    -2.33
    as
    -2.31
    POSITIVE LOGITS
     fhall
    2.78
    噚
    2.59
     diza
    2.55
    婓
    2.45
     ftill
    2.42
    ✃
    2.42
    芣
    2.41
     fhould
    2.41
     themſelves
    2.39
     dibujado
    2.38
    Activations Density 0.005%

    No Known Activations