© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34479
    Prev
    Next
    INDEX
    Explanations

    can accommodate people or seats

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    alignSelf
    -0.78
    単位
    -0.77
    Ạ
    -0.75
    alleries
    -0.74
    ガ
    -0.71
     جبل
    -0.69
     Иванович
    -0.68
    ជ
    -0.68
    Aplica
    -0.68
    lead
    -0.68
    POSITIVE LOGITS
     accommodate
    3.69
     accommodates
    3.52
     accommodating
    3.38
     accomod
    3.00
     accommodated
    2.75
     accommodation
    2.42
    commod
    2.36
     capacity
    2.19
     accommodations
    2.16
     accommod
    2.08
    Activations Density 0.077%

    No Known Activations