© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22636
    Prev
    Next
    INDEX
    Explanations

    topics, buckets, index

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     inuti
    -1.62
    мі
    -1.54
     judicia
    -1.43
    阄
    -1.39
     nossos
    -1.31
     oeuvres
    -1.29
    鹩
    -1.28
     éx
    -1.25
     potes
    -1.25
    amitié
    -1.24
    POSITIVE LOGITS
    可以
    1.34
    }[!
    1.30
    inobu
    1.24
    ]
    1.22
    である
    1.22
     thier
    1.21
     են
    1.20
     Američ
    1.20
    Omg
    1.16
     name
    1.16
    Activations Density 0.030%

    No Known Activations