© 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. 231510
    Prev
    Next
    INDEX
    Explanations

    .gov and .org domains

    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
    ಳಗ
    0.50
     नाक
    0.48
    ्हान
    0.47
    ঘুম
    0.47
    Poems
    0.47
     ট্রেন
    0.46
     নাইট
    0.46
    ᱪ
    0.46
     বিনি
    0.45
    клу
    0.45
    POSITIVE LOGITS
    t
    0.52
     $
    0.52
     .
    0.50
     bure
    0.46
     tall
    0.46
    $
    0.45
     her
    0.45
    趋
    0.44
     bas
    0.43
     Māori
    0.43
    Activations Density 0.000%

    No Known Activations