© 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. 72498
    Prev
    Next
    INDEX
    Explanations

    multilingual words and technical terms

    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
    ActionButton
    -0.87
    龶
    -0.82
    它的
    -0.81
    präsident
    -0.80
    -}
    -0.80
    ")));
    -0.79
    {*}
    -0.78
    }(),
    -0.77
     And
    -0.76
     مجلس
    -0.76
    POSITIVE LOGITS
    /
    1.12
    pēc
    0.86
     nepiecieš
    0.85
    historique
    0.83
     dejaron
    0.83
     découv
    0.82
     apoya
    0.82
    əri
    0.82
     hvorfor
    0.80
    buon
    0.79
    Activations Density 0.153%

    No Known Activations