© 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. 173910
    Prev
    Next
    INDEX
    Explanations

    fee, old, usage, partial, prizes, lessons

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

    general idea

    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
     polícia
    0.54
    。“
    0.47
     собстве
    0.46
     właścic
    0.45
     decât
    0.45
    ।
    0.44
     संज्ञा
    0.43
     白
    0.42
     د
    0.42
     počas
    0.42
    POSITIVE LOGITS
    ylene
    0.47
    yscraper
    0.46
    다음
    0.45
    룰
    0.45
     FLAGS
    0.45
    ⎟
    0.42
    눗
    0.41
    ｳ
    0.41
     اولمپ
    0.41
    মূলক
    0.41
    Activations Density 0.007%

    No Known Activations