© 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. 34-GEMMASCOPE-RES-131K
    7. 2882
    Prev
    Next
    INDEX
    Explanations

    types of homes and buildings

    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
    boretum
    -0.89
     tượng
    -0.89
     χω
    -0.83
    baguna
    -0.82
    induction
    -0.82
    ţa
    -0.81
    zeiro
    -0.78
     village
    -0.77
     Hazel
    -0.75
    сыла
    -0.74
    POSITIVE LOGITS
     mansion
    1.51
     townhouse
    1.37
     house
    1.32
     mansions
    1.26
     houses
    1.11
     residential
    1.07
     merchant
    1.06
     palace
    1.05
     House
    1.00
     private
    0.95
    Activations Density 0.041%

    No Known Activations