© 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. 30889
    Prev
    Next
    INDEX
    Explanations

    More followed by elaborations

    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
    estimated
    -1.04
    recorded
    -1.00
    連れ
    -0.97
    certainly
    -0.95
    receive
    -0.94
    already
    -0.93
    vábbi
    -0.93
    你了
    -0.92
    ライター
    -0.92
    følge
    -0.91
    POSITIVE LOGITS
     than
    2.19
     importantly
    2.03
     likely
    1.59
     specifically
    1.45
     often
    1.29
     accurately
    1.28
     about
    1.26
     to
    1.26
     details
    1.24
     people
    1.19
    Activations Density 0.034%

    No Known Activations