© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 3856
    Prev
    Next
    INDEX
    Explanations

    React components and UI definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    j
    0.41
    At
    0.39
    _,
    0.39
    math
    0.38
    atum
    0.38
    ona
    0.38
    ayan
    0.37
     Orth
    0.37
    play
    0.37
    ayam
    0.37
    POSITIVE LOGITS
     /></
    0.47
     />}
    0.47
    тира
    0.42
    激安
    0.41
    xmlns
    0.40
    छा
    0.39
     berjudul
    0.39
    ⬥
    0.39
     {...
    0.38
     />;
    0.38
    Activations Density 0.102%

    No Known Activations