© 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. 34-GEMMASCOPE-RES-131K
    7. 12165
    Prev
    Next
    INDEX
    Explanations

    questions and specific answers

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

    The neuron primarily detects question marks (i.e. interrogative punctuation).

    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
    っそ
    -1.03
     auroit
    -1.00
     Furthermore
    -1.00
     HomeScreen
    -0.98
     همین
    -0.95
     setOpen
    -0.93
     Lastly
    -0.93
     Также
    -0.93
     Moreover
    -0.91
     OGSÅ
    -0.90
    POSITIVE LOGITS
     you
    1.46
    </h2>
    1.23
     forstå
    1.20
     אתה
    1.12
     tidligere
    1.11
    或
    1.11
     вашим
    1.10
    ↵↵
    1.09
    Apakah
    1.09
     bestemt
    1.09
    Activations Density 0.007%

    No Known Activations