© 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. 10-GEMMASCOPE-RES-131K
    7. 113281
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers

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

    The neuron fires on long sequences of repeated uppercase letters.

    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
     Añade
    -2.16
    ଃ
    -2.05
     Agrega
    -1.95
     who
    -1.94
     Obtén
    -1.93
     atualmente
    -1.86
    罴
    -1.86
     Lleva
    -1.82
     recém
    -1.82
    ").
    -1.81
    POSITIVE LOGITS
    y
    2.28
    e
    1.90
     they
    1.86
    以上です
    1.84
    籥
    1.80
     joka
    1.79
     aikaa
    1.73
     accessoire
    1.73
    —
    1.72
     oiseau
    1.70
    Activations Density 0.042%

    No Known Activations