© 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. 128131
    Prev
    Next
    INDEX
    Explanations

    think or reflect on something

    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
    Zubereitung
    -1.69
    Kommentare
    -1.57
     vecchio
    -1.46
    ➢
    -1.46
     coraggio
    -1.46
     strumenti
    -1.45
     latter
    -1.45
     piccole
    -1.44
     troviamo
    -1.42
     giovane
    -1.40
    POSITIVE LOGITS
     what
    1.72
     how
    1.66
     why
    1.44
     where
    1.41
     about
    1.37
    openhauer
    1.34
     他
    1.33
     péld
    1.33
    らなかった
    1.32
    béco
    1.31
    Activations Density 0.016%

    No Known Activations