© 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. 25960
    Prev
    Next
    INDEX
    Explanations

    types of lodging

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

    The neuron detects mentions of lodging or accommodation establishments (e.g. names and types like Motel, Lodge, B&B, Pension, Hotel).

    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
     from
    -1.11
    prender
    -1.11
    D
    -1.10
     Gehäuse
    -1.06
     beispielsweise
    -1.05
     spécialisée
    -1.02
    Power
    -1.01
     Cedex
    -1.01
     spécialisé
    -1.00
    potentially
    -1.00
    POSITIVE LOGITS
     dentes
    1.27
     ló
    1.25
     HttpHeaders
    1.19
    Tariff
    1.19
    grafen
    1.18
     dí
    1.14
     cuchillo
    1.14
    1.13
     réfrigérateur
    1.13
    Albums
    1.11
    Activations Density 0.021%

    No Known Activations