© 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. 34-GEMMASCOPE-RES-131K
    7. 63313
    Prev
    Next
    INDEX
    Explanations

    types of accommodation

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

    The neuron is activated by words naming small lodging or accommodation types (e.g. cottage, cabin, lodge, barn).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ⎆
    -0.94
    DeleteBehavior
    -0.90
     २०
    -0.88
    varer
    -0.87
     słon
    -0.86
     phare
    -0.85
     thuật
    -0.84
     enceinte
    -0.84
     czo
    -0.83
     bushes
    -0.82
    POSITIVE LOGITS
     style
    1.20
     on
    1.10
     with
    1.04
     in
    1.04
     owners
    0.96
     built
    0.95
    式
    0.95
     type
    0.94
     owned
    0.93
     accommodation
    0.91
    Activations Density 0.024%

    No Known Activations