© 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. 76630
    Prev
    Next
    INDEX
    Explanations

    code path separators and identifiers

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

    The neuron strongly fires on Unicode‐escape sequences (e.g. “\uXXXX”) inside 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
    tawesome
    -0.74
    Coucou
    -0.72
     liberation
    -0.71
    💒
    -0.70
    rededor
    -0.70
     Décor
    -0.69
    쌈
    -0.69
     Suppression
    -0.69
    demia
    -0.69
     realms
    -0.69
    POSITIVE LOGITS
    ................
    0.79
     переза
    0.78
    tora
    0.78
    Few
    0.77
     few
    0.75
    dagen
    0.72
    ikt
    0.72
     والت
    0.72
    arching
    0.71
    rsch
    0.71
    Activations Density 0.031%

    No Known Activations