© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2733
    Prev
    Next
    INDEX
    Explanations

    outdoor spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     museums
    0.51
     Euse
    0.51
    辞典
    0.50
    賃
    0.50
     musée
    0.50
    cognitive
    0.50
     hypothalamus
    0.49
     Cognitive
    0.49
     radiology
    0.49
     ħ
    0.49
    POSITIVE LOGITS
     patio
    2.11
     patios
    1.94
     Patio
    1.92
     outdoor
    1.87
     porch
    1.84
     backyard
    1.80
     terrace
    1.79
     veranda
    1.78
     Outdoor
    1.74
    outdoor
    1.72
    Activations Density 0.727%

    No Known Activations