© 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. 81681
    Prev
    Next
    INDEX
    Explanations

    daily medication

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

    eggs and love

    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
    <0x80>
    0.52
     szczegól
    0.51
     któ
    0.51
     لیګ
    0.50
    يري
    0.50
    ॢ
    0.49
    圈
    0.49
     współpr
    0.48
     ismi
    0.47
    ジット
    0.46
    POSITIVE LOGITS
    <(),
    0.49
     malls
    0.47
     प्रभावशाली
    0.47
     Humidity
    0.47
     Dead
    0.46
    aches
    0.46
     Utils
    0.46
     analges
    0.45
    を除
    0.45
    jections
    0.45
    Activations Density 0.001%

    No Known Activations