© 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. 30740
    Prev
    Next
    INDEX
    Explanations

    relocation of space

    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
     устройство
    -0.90
    LETON
    -0.89
    綻
    -0.85
     フリー
    -0.85
    ORING
    -0.81
     höch
    -0.81
     Deletion
    -0.81
     eingeführt
    -0.81
    Deletion
    -0.81
    izzare
    -0.80
    POSITIVE LOGITS
     location
    1.88
     space
    1.83
     relocation
    1.74
     spacious
    1.69
    location
    1.64
     leased
    1.61
     lease
    1.59
     relocate
    1.58
     premises
    1.55
     moved
    1.54
    Activations Density 0.072%

    No Known Activations