© 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. 14748
    Prev
    Next
    INDEX
    Explanations

    separate residential units

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

    The neuron detects mentions of specific types of living quarters or accommodation units (e.g., suite, apartment, duplex) in property 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
     auswählen
    -1.23
     Technologien
    -1.21
     straips
    -1.12
     möglichst
    -1.08
     fehler
    -1.06
     erstmals
    -1.05
    $,
    -1.05
     ausgewählt
    -1.05
     someplace
    -1.05
     irgendwo
    -1.04
    POSITIVE LOGITS
    كامل
    1.12
     with
    1.09
     separate
    1.06
     separable
    1.04
    对外
    1.03
     another
    1.02
    separated
    1.02
    ////////
    1.01
    ıkları
    1.00
     separated
    1.00
    Activations Density 0.010%

    No Known Activations