© 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. 33492
    Prev
    Next
    INDEX
    Explanations

    answers to questions

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

    The neuron strongly activates on question sentences—particularly on question‐mark 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_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
     También
    -1.05
    ٧
    -1.01
    новен
    -1.01
     także
    -1.00
     también
    -0.97
    atives
    -0.97
     dessutom
    -0.96
    也
    -0.96
     jeweils
    -0.96
     também
    -0.95
    POSITIVE LOGITS
     yes
    1.94
     YES
    1.72
    YES
    1.59
    Yes
    1.51
     Yes
    1.45
    結論
    1.41
    いかがでしたか
    1.39
    是可以
    1.34
    yes
    1.19
     depending
    1.16
    Activations Density 0.066%

    No Known Activations