© 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. 22-GEMMASCOPE-RES-131K
    7. 26834
    Prev
    Next
    INDEX
    Explanations

    rooms and furniture

    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_22/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
     områ
    -1.37
     gått
    -1.23
    mortem
    -1.20
     ρ
    -1.19
     går
    -1.17
     kroppen
    -1.13
    itemize
    -1.06
     dismal
    -1.05
    在一
    -1.04
     دندان
    -1.03
    POSITIVE LOGITS
     three
    1.35
     of
    1.31
    pousada
    1.16
     first
    1.13
     or
    1.13
     four
    1.09
    weite
    1.09
     every
    1.07
     any
    1.06
     two
    1.06
    Activations Density 0.054%

    No Known Activations