© 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. 3802
    Prev
    Next
    INDEX
    Explanations

    SEO, product, financial, blog, replacement

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

    football, coco, exams

    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
     dot
    0.53
     Dot
    0.53
     UCI
    0.52
    的天
    0.51
    ច្រើន
    0.51
    3
    0.51
     en
    0.50
    o
    0.50
     owner
    0.50
     cari
    0.50
    POSITIVE LOGITS
    訝
    0.54
    जफ्
    0.50
    坊
    0.50
    ાવો
    0.50
     "?"]
    0.49
    報告
    0.48
    িদ্ধ
    0.48
    にあった
    0.47
    慥
    0.47
    હાસ
    0.46
    Activations Density 0.000%

    No Known Activations