© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 125400
    Prev
    Next
    INDEX
    Explanations

    medical conditions or specific terms

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

    complex topics

    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
     올해
    0.56
     वैष्ण
    0.54
    Export
    0.49
     &.
    0.48
     ochrony
    0.48
     ถ้า
    0.48
     ĝi
    0.48
     없
    0.47
    літы
    0.47
     ©️
    0.47
    POSITIVE LOGITS
    ural
    0.49
     sounded
    0.46
    ibile
    0.46
    rog
    0.45
     lengthened
    0.43
    ﭼ
    0.43
     hospitalized
    0.42
     potentially
    0.42
     speculated
    0.42
     stochastic
    0.42
    Activations Density 0.001%

    No Known Activations