© 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. 76383
    Prev
    Next
    INDEX
    Explanations

    description of homes

    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
    公寓
    -1.27
    Apartment
    -1.02
     apartment
    -0.95
     apartments
    -0.93
     Apartment
    -0.91
    Apartments
    -0.90
     Apartments
    -0.90
     tenement
    -0.80
     दुनिया
    -0.77
    vičius
    -0.76
    POSITIVE LOGITS
     brick
    1.56
     home
    1.34
     ladrillo
    1.13
     executive
    1.09
     Brick
    1.08
     Crafts
    1.04
    brick
    1.03
     homes
    1.02
     family
    1.00
     custom
    1.00
    Activations Density 0.036%

    No Known Activations