© 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. 15829
    Prev
    Next
    INDEX
    Explanations

    special characters delimiters

    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
    );
    -2.06
    s
    -1.66
     a
    -1.65
    owanie
    -1.52
     empezar
    -1.51
    -..
    -1.51
     my
    -1.48
     ネット
    -1.42
     márm
    -1.39
    )
    -1.38
    POSITIVE LOGITS
    9
    1.92
     hamper
    1.82
    {~
    1.77
     According
    1.73
    ꜆
    1.68
    3
    1.66
     такі
    1.65
     рекомендуется
    1.64
     letzten
    1.63
     repentance
    1.59
    Activations Density 0.028%

    No Known Activations