© 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. 10-GEMMASCOPE-RES-131K
    7. 60547
    Prev
    Next
    INDEX
    Explanations

    motel or motility

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

    The neuron strongly activates on terms naming motel‐style lodging (e.g., “motel,” “motor lodge,” “complex”).

    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
    ஂ
    -2.16
    呦
    -2.09
    which
    -2.06
    衪
    -2.05
     steeped
    -1.97
    ۔
    -1.95
    ࿆
    -1.95
    。】
    -1.95
    ></
    -1.95
    ats
    -1.89
    POSITIVE LOGITS
    ";
    2.08
     otras
    2.08
     To
    2.06
    ⩴
    2.03
    ㆆ
    2.03
    ῞
    1.97
    何とか
    1.95
    .
    1.91
     altre
    1.87
    楽しむ
    1.86
    Activations Density 0.004%

    No Known Activations