© 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. 99369
    Prev
    Next
    INDEX
    Explanations

    eliminating property blight

    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
     garan
    -0.89
     peasants
    -0.86
    Xu
    -0.84
     Sotto
    -0.84
    uder
    -0.83
     quæ
    -0.81
    がついて
    -0.81
     officinalis
    -0.79
     inger
    -0.79
     Biotechnol
    -0.79
    POSITIVE LOGITS
     boarded
    1.42
     property
    1.27
     vacant
    1.25
     properties
    1.21
     rehab
    1.12
     blight
    1.09
     inspectors
    1.04
     condemn
    1.01
     code
    0.99
     getCode
    0.96
    Activations Density 0.018%

    No Known Activations