© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75117
    Prev
    Next
    INDEX
    Explanations

    “ or [ followed by text

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

    The neuron fires on quotation‐mark tokens that introduce quoted or block-quoted text (i.e. opening quote 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_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
     phénom
    -1.47
     méda
    -1.36
    holen
    -1.30
     développe
    -1.27
     Traducción
    -1.26
     constater
    -1.25
    Πηγή
    -1.23
    increases
    -1.23
     Aseg
    -1.23
    voorbeeld
    -1.23
    POSITIVE LOGITS
     to
    1.67
     all
    1.43
     (
    1.43
     [
    1.39
     our
    1.28
    ),
    1.27
     $
    1.24
    _
    1.23
     about
    1.19
     La
    1.19
    Activations Density 0.001%

    No Known Activations