© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130367
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on nouns naming physical amenities, facilities, or site-specific features (e.g. climate control, kitchenette, mountain view, outdoor hard courts, bathtub).

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

    sports courts and broadcasting

    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
     quidem
    -1.02
     sinon
    -1.01
     moft
    -1.00
    \#:
    -0.98
     gratuite
    -0.97
     eorum
    -0.97
    工厂
    -0.97
     fhould
    -0.96
     tény
    -0.96
    癀
    -0.94
    POSITIVE LOGITS
    liferation
    1.13
    仍然
    1.04
     here
    1.02
    Preparazione
    1.00
    archar
    0.99
    ğmen
    0.98
     if
    0.94
    positories
    0.94
     тут
    0.93
     probablemente
    0.93
    Activations Density 0.025%

    No Known Activations