© 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. 130171
    Prev
    Next
    INDEX
    Explanations

    edges as, need in, proverbial weed, compromising

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

    evaluating objects or data

    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
    发现了
    0.59
     démontré
    0.55
    newMessage
    0.46
     দেখেছেন
    0.46
    有关
    0.45
     પાસેથી
    0.44
    șt
    0.44
    lyPlugin
    0.44
     调用
    0.44
    ﮄ
    0.43
    POSITIVE LOGITS
    Й
    0.50
     hurry
    0.47
     redu
    0.44
    Cada
    0.44
     .
    0.43
    improve
    0.43
    OK
    0.43
    飒
    0.42
     красо
    0.42
    из
    0.42
    Activations Density 0.000%

    No Known Activations