© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15982
    Prev
    Next
    INDEX
    Explanations

    receives input or origin

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

    This neuron selectively responds to domain-specific technical and scientific terminology—specialized nouns and key technical terms common in research or highly formal technical writing.

    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
    creating
    -0.91
     сотрудни
    -0.82
    PostConstruct
    -0.82
    Warn
    -0.81
    
    -0.79
    DATABASES
    -0.78
     extravag
    -0.78
    ؤلاء
    -0.77
     AFC
    -0.77
    then
    -0.75
    POSITIVE LOGITS
     receive
    1.56
     received
    1.54
     receives
    1.53
     from
    1.53
     external
    1.49
     by
    1.44
     receiving
    1.40
    来自
    1.36
    來自
    1.27
     incoming
    1.24
    Activations Density 0.238%

    No Known Activations