© 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. 139554
    Prev
    Next
    INDEX
    Explanations

    dental, cards, misleading

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

    acceptance and offers

    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
    انج
    0.51
    ر
    0.48
    herd
    0.48
     geçti
    0.48
    Andre
    0.47
    Alien
    0.47
     artères
    0.47
    بية
    0.47
    슨
    0.46
    Adds
    0.45
    POSITIVE LOGITS
    {
    0.54
     ine
    0.49
     type
    0.48
     errores
    0.48
     {.
    0.47
     seam
    0.45
     Type
    0.44
     error
    0.44
     UV
    0.44
    nament
    0.44
    Activations Density 0.002%

    No Known Activations