© 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. 27708
    Prev
    Next
    INDEX
    Explanations

    questions and comparisons

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

    The neuron detects the presence of interrogative prompts—phrases and words that introduce or form questions.

    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
     was
    -1.04
     usually
    -0.98
    </td>
    -0.91
    toDate
    -0.91
     ofta
    -0.90
    matory
    -0.88
     Usually
    -0.82
    manı
    -0.82
     конкре
    -0.80
    utable
    -0.80
    POSITIVE LOGITS
     since
    1.04
    retts
    0.96
     genauso
    0.96
     SUMMER
    0.94
     then
    0.93
     asimismo
    0.93
     ebenfalls
    0.91
    uero
    0.91
     setiap
    0.90
    一樣
    0.90
    Activations Density 0.028%

    No Known Activations