© 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. 107507
    Prev
    Next
    INDEX
    Explanations

    photograph of Pimples

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

    core principles and goals

    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
    it
    0.46
    ú
    0.43
    ène
    0.43
    KI
    0.42
    ulina
    0.42
     entrap
    0.41
     capture
    0.40
    ის
    0.40
     ligation
    0.40
    不断
    0.40
    POSITIVE LOGITS
     naszej
    0.48
     Denison
    0.48
     świecie
    0.48
     przyp
    0.47
    ত
    0.47
     sắt
    0.47
     nasze
    0.47
    দেখে
    0.46
     নিক
    0.46
     Agh
    0.46
    Activations Density 0.001%

    No Known Activations