© 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. 10-GEMMASCOPE-RES-131K
    7. 39564
    Prev
    Next
    INDEX
    Explanations

    types of establishments

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

    The neuron activates on words naming specific venues or establishments (e.g., restaurants, salons, hospitals, institutes, hotels, bars, companies).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     about
    -1.49
    pography
    -1.38
     until
    -1.32
    stalgia
    -1.31
     так
    -1.22
     another
    -1.16
     lusso
    -1.14
    odles
    -1.13
    public
    -1.13
     into
    -1.12
    POSITIVE LOGITS
    carnated
    1.34
    続く
    1.32
    чает
    1.30
     rallado
    1.30
     Jego
    1.29
     lejos
    1.27
    NEET
    1.27
    뮌
    1.27
     especializada
    1.26
    hoots
    1.26
    Activations Density 0.021%

    No Known Activations