© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85812
    Prev
    Next
    INDEX
    Explanations

    he who, throughout history, of souls

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

    or walk by again

    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
    Negative Logits
    на
    0.45
     afgelopen
    0.45
    难题
    0.42
    assays
    0.41
    કો
    0.40
     unwell
    0.40
    `).
    0.40
    கடந்த
    0.40
    Malay
    0.39
    課題
    0.39
    POSITIVE LOGITS
     ছোট্ট
    0.46
     ใส่
    0.46
     ส่ง
    0.46
     เชื่อ
    0.45
     เส
    0.44
     ጎ
    0.44
     让
    0.44
     ち
    0.44
     peonies
    0.43
     ขาย
    0.43
    Activations Density 0.000%

    No Known Activations