© 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. 34-GEMMASCOPE-RES-131K
    7. 77168
    Prev
    Next
    INDEX
    Explanations

    property and prop

    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
    Traceback
    -0.85
    Plans
    -0.78
    Perez
    -0.77
     münd
    -0.77
     Perez
    -0.76
    Pennsylvania
    -0.75
     ajoute
    -0.75
    願
    -0.74
     Pérez
    -0.74
    RegistryLite
    -0.73
    POSITIVE LOGITS
     property
    4.53
     properties
    3.81
     prop
    3.50
     Property
    3.41
    prop
    3.22
    property
    3.20
     props
    3.13
    Property
    3.09
     Prop
    3.06
    Prop
    3.05
    Activations Density 0.038%

    No Known Activations