© 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. 93131
    Prev
    Next
    INDEX
    Explanations

    code or non-English

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

    The neuron selectively activates on non-ASCII or non-Latin script sequences (e.g. Chinese characters or other high-byte 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
    fél
    -0.75
    boretum
    -0.75
    Perhaps
    -0.72
     éter
    -0.72
    uyez
    -0.71
    Liefer
    -0.71
    Basically
    -0.70
    医者
    -0.70
    لوب
    -0.70
     Combining
    -0.69
    POSITIVE LOGITS
    SYNOPSIS
    0.84
    층
    0.80
     Erişim
    0.79
    yeon
    0.77
     !!}
    0.77
    ストリー
    0.77
     PLOS
    0.75
    oczes
    0.75
     DEM
    0.74
     Toy
    0.73
    Activations Density 0.002%

    No Known Activations