© 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. 22-GEMMASCOPE-RES-131K
    7. 38700
    Prev
    Next
    INDEX
    Explanations

    quoted strings or identifiers

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

    The neuron is responding to standalone single‐quote characters (the apostrophe token) used to delimit strings or attribute values.

    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
     sonrisa
    -1.41
    didSet
    -1.31
    
    -1.22
    戕
    -1.21
    もあって
    -1.16
     personalizadas
    -1.15
     tirs
    -1.13
    厝
    -1.13
     ombro
    -1.11
     personalizada
    -1.10
    POSITIVE LOGITS
    ."
    1.16
     kurie
    1.15
     lol
    1.13
    谖
    1.13
     brachte
    1.11
     ésta
    1.10
     zumal
    1.10
     lecz
    1.08
     hacía
    1.07
     insulting
    1.07
    Activations Density 0.002%

    No Known Activations