© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219615
    Prev
    Next
    INDEX
    Explanations

    stones, furniture, finance, shops, and inspiration

    np_acts-logits-general · gemini-2.5-flash-lite

    what makes something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conflicts
    0.44
    吳
    0.44
    Conflicts
    0.41
    Unless
    0.41
     Carm
    0.40
    कान
    0.40
    Normally
    0.39
     Theoretically
    0.39
    ле
    0.39
     доб
    0.39
    POSITIVE LOGITS
    aliers
    0.52
     作り
    0.52
    ié
    0.51
     Пас
    0.50
    槭
    0.49
     kios
    0.48
    daten
    0.48
    ในปี
    0.46
    杵
    0.46
    owntown
    0.46
    Activations Density 0.001%

    No Known Activations