© 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. 10-GEMMASCOPE-RES-131K
    7. 128688
    Prev
    Next
    INDEX
    Explanations

    bathrooms and houses

    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_10/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
    却被
    -1.24
     celý
    -1.24
    寻求
    -1.22
    ⤞
    -1.22
     kvůli
    -1.22
     BRARY
    -1.20
    紆
    -1.20
     gegeven
    -1.19
     použit
    -1.18
     krijgen
    -1.17
    POSITIVE LOGITS
    They
    1.48
     these
    1.38
     they
    1.32
     a
    1.29
    These
    1.27
                    
    1.24
     bathrooms
    1.21
     keren
    1.18
     entonces
    1.18
    ↵
    1.15
    Activations Density 0.006%

    No Known Activations