© 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. 67992
    Prev
    Next
    INDEX
    Explanations

    fireplace, floors, ceilings, vanity, granite

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

    The neuron is responsive to mentions of specific building materials and architectural details (e.g. stone, marble, vaulted, travertine) in real-estate descriptions.

    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
     poszczegól
    -1.17
     açıklama
    -1.16
    ἃ
    -1.16
    mayın
    -1.10
     cumplen
    -1.09
    oxia
    -1.09
     لهذه
    -1.08
     bakteri
    -1.07
    첫
    -1.07
     разнообраз
    -1.06
    POSITIVE LOGITS
     (;;)
    1.12
     an
    1.11
     上午
    1.05
     a
    1.05
     Horses
    1.02
    𝘪
    1.02
    '"
    1.01
     ?"
    1.01
    들
    0.99
     DevComponents
    0.98
    Activations Density 0.008%

    No Known Activations