© 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. 15920
    Prev
    Next
    INDEX
    Explanations

    end of quote, end of sentence

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

    The neuron is specialized in spotting bits of direct speech—that is, text enclosed in quotation marks (spoken quotations).

    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
     without
    -1.33
     others
    -1.27
     després
    -1.17
     allowing
    -1.16
     at
    -1.12
     as
    -1.11
    鋲
    -1.10
     italiano
    -1.09
     encara
    -1.09
    🆚
    -1.09
    POSITIVE LOGITS
     soltanto
    1.41
     confirmó
    1.25
     pokrač
    1.25
     капю
    1.25
    ("")){
    1.24
    つづく
    1.24
     unſ
    1.21
     capuz
    1.21
    んでる
    1.21
     consiguiente
    1.19
    Activations Density 0.016%

    No Known Activations