© 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. 91548
    Prev
    Next
    INDEX
    Explanations

    quotation marks and similar punctuation

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

    This neuron detects hexadecimal‐style escape sequences (tokens like “xe2”, “x80”, “x9c”, “x9d”, etc.) representing encoded non-ASCII characters.

    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
    ..\..\
    -0.85
    カウンター
    -0.84
    カスタ
    -0.77
    Inne
    -0.77
     wody
    -0.77
     hiver
    -0.77
    本田
    -0.76
     그것
    -0.76
     noiva
    -0.75
     sages
    -0.73
    POSITIVE LOGITS
     "
    1.69
     “
    1.54
    ldquo
    1.39
     '
    1.38
    quot
    1.23
     \"
    1.20
    "
    1.20
    “
    1.14
     ‘
    1.13
    『
    1.07
    Activations Density 0.043%

    No Known Activations