© 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. 128655
    Prev
    Next
    INDEX
    Explanations

    The neuron spotlights mentions of high-end home features and upgrades—detailed amenities, fixtures, and technical specifications.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    architectural details and materials

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     or
    -1.30
    rinted
    -1.23
     dowol
    -1.21
    ῖς
    -1.21
     aislados
    -1.21
     doká
    -1.19
     découvrez
    -1.18
     skupina
    -1.15
    Altre
    -1.15
     it
    -1.15
    POSITIVE LOGITS
     all
    1.48
     anvä
    1.23
     also
    1.22
     faktiskt
    1.21
    所有的
    1.21
     bouteille
    1.20
     toate
    1.16
     verkligen
    1.12
     även
    1.11
     всем
    1.10
    Activations Density 0.015%

    No Known Activations