© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64673
    Prev
    Next
    INDEX
    Explanations

    charged, granted, taken, found, given, arrested

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    -1.20
    FOREWORD
    -1.17
     ujedno
    -1.17
     that
    -1.11
     suatu
    -1.09
    与此同时
    -1.09
    そのため
    -1.06
    Otros
    -1.05
    leyebilirsiniz
    -1.04
     importanti
    -1.03
    POSITIVE LOGITS
     aDecoder
    1.24
    muñeca
    1.14
    很多人
    1.13
    解釋
    1.11
    ִּ
    1.09
    
    1.09
    тся
    1.09
     Commencez
    1.07
     Trouvez
    1.07
    ditionally
    1.05
    Activations Density 0.052%

    No Known Activations