© 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. 22-GEMMASCOPE-RES-131K
    7. 79529
    Prev
    Next
    INDEX
    Explanations

    build, studies, watch

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

    The neuron fires on informative, explanatory prose—passages that describe what to do, how things work, or report technical/clinical findings.

    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
    的一声
    -1.00
     enormes
    -0.97
     ConstraintSet
    -0.94
    ตอบ
    -0.93
    こな
    -0.93
    子育て
    -0.90
    在这种
    -0.90
     هؤلاء
    -0.89
    خخ
    -0.88
    自从
    -0.88
    POSITIVE LOGITS
     our
    1.77
     product
    1.20
    Our
    1.16
     हमारे
    1.09
     нашей
    1.07
     powierzch
    1.05
    lossary
    1.04
     наших
    1.02
    !”
    1.01
    Download
    1.00
    Activations Density 0.288%

    No Known Activations