© 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. 115712
    Prev
    Next
    INDEX
    Explanations

    loft, attic, floor, balcony

    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
     dined
    -0.90
     indoors
    -0.82
     Outdoors
    -0.79
     igualdad
    -0.79
    clonal
    -0.78
     downstairs
    -0.78
     lowers
    -0.75
     cellars
    -0.73
    地下
    -0.73
     downhill
    -0.71
    POSITIVE LOGITS
     loft
    2.06
     landing
    1.85
     Loft
    1.67
    loft
    1.65
    landing
    1.49
    Landing
    1.49
     Landing
    1.41
    Loft
    1.36
     attic
    1.28
     balcony
    1.25
    Activations Density 0.014%

    No Known Activations