© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24907
    Prev
    Next
    INDEX
    Explanations

    also, specifically, end, delay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     primeiras
    0.21
    )
    0.18
     وأ
    0.18
    }
    0.18
     vezes
    0.17
     أش
    0.17
     و
    0.17
    러스
    0.17
    rath
    0.17
    ,
    0.17
    POSITIVE LOGITS
     tehát
    0.23
     also
    0.23
     उपरोक्त
    0.22
     также
    0.22
     ასევე
    0.22
    上記の
    0.21
     ALSO
    0.20
     Also
    0.20
    とにかく
    0.20
     Specifically
    0.20
    Activations Density 0.080%

    No Known Activations