© 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. 22-GEMMASCOPE-RES-131K
    7. 65641
    Prev
    Next
    INDEX
    Explanations

    INTRODUCTION, Proclamation, Be Not Nobody

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

    The neuron detects hexadecimal escape sequences (e.g. URL‐style “%xx” encodings and “\u” Unicode escapes) in 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_22/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
    The
    -1.56
    Although
    -1.55
    It
    -1.54
    Despite
    -1.52
    With
    -1.52
    Unlike
    -1.51
     In
    -1.50
    what
    -1.49
     what
    -1.48
     can
    -1.45
    POSITIVE LOGITS
     chcete
    1.31
     nôtre
    1.26
     jednej
    1.26
     budeme
    1.23
     Brings
    1.23
     enraged
    1.23
     verranno
    1.19
     cadeiras
    1.18
     prachtige
    1.18
     horrid
    1.18
    Activations Density 0.002%

    No Known Activations