© 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. 21443
    Prev
    Next
    INDEX
    Explanations

    house or 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_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
    とその
    -2.36
    驁
    -2.14
    ?
    -2.02
     菇
    -1.97
     consequ
    -1.95
     vrijdag
    -1.89
    梱
    -1.89
    牁
    -1.86
     dezelfde
    -1.84
    のもと
    -1.84
    POSITIVE LOGITS
    ?”
    2.36
     {
    2.36
     get
    2.25
     *
    2.22
     have
    2.11
     автомобиль
    2.09
    )/
    2.03
    laz
    2.03
    (\
    2.02
     neue
    2.02
    Activations Density 0.002%

    No Known Activations