© 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. 72934
    Prev
    Next
    INDEX
    Explanations

    questions about benefits or projects

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

    This neuron activates on content words inside interrogative prompts—that is, it detects tokens occurring within question sentences.

    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
     Because
    -1.30
     quickly
    -1.27
     هایی
    -1.23
     profoundly
    -1.23
     unquestionably
    -1.23
    íme
    -1.20
     verificare
    -1.17
    ８
    -1.16
     low
    -1.15
    ६
    -1.15
    POSITIVE LOGITS
    っていたので
    1.40
     quels
    1.30
     chacun
    1.30
    </h2>
    1.27
     étions
    1.27
     regiões
    1.25
     vaše
    1.23
     cães
    1.23
    especially
    1.21
    </strong>
    1.19
    Activations Density 0.014%

    No Known Activations