© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10669
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on mentions of offered guest services or amenities—especially named facilities (like “luggage storage,” “Free Wi-Fi,” “kitchen”) and their availability hours.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Enfer
    0.78
     bề
    0.77
     обеспе
    0.77
    <unused69>
    0.74
     forefront
    0.74
     FODC
    0.73
     обеспечения
    0.72
     vượt
    0.72
     femora
    0.72
     flax
    0.71
    POSITIVE LOGITS
    ان
    0.91
    Type
    0.76
    b
    0.72
    ن
    0.72
    all
    0.70
     '
    0.68
    an
    0.66
     millioner
    0.66
    piel
    0.66
    に使
    0.66
    Activations Density 0.000%

    No Known Activations