© 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. 64269
    Prev
    Next
    INDEX
    Explanations

    interior upholstery materials

    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
    organizzazione
    -0.81
     Administr
    -0.77
     physiology
    -0.75
    disk
    -0.74
     Corruption
    -0.73
     administr
    -0.73
     Russland
    -0.71
    lifying
    -0.70
     Fenton
    -0.70
     administration
    -0.69
    POSITIVE LOGITS
     upholstery
    2.02
     leather
    1.69
     seats
    1.68
     fabric
    1.65
     uphol
    1.63
     seat
    1.38
     reu
    1.32
     Uphol
    1.32
    Seats
    1.31
    seats
    1.30
    Activations Density 0.017%

    No Known Activations