© 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. 16312
    Prev
    Next
    INDEX
    Explanations

    location or group identifiers

    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
     nadat
    -1.02
     handen
    -0.99
    alogie
    -0.98
    iapkan
    -0.98
     zowel
    -0.98
     aanv
    -0.97
    ústria
    -0.97
    ıyla
    -0.97
    itário
    -0.97
    푠
    -0.96
    POSITIVE LOGITS
    ஞ
    0.90
    特に
    0.85
    إن
    0.83
    అ
    0.83
    mening
    0.83
    Тек
    0.82
     появится
    0.81
     will
    0.81
     będ
    0.81
     सभी
    0.80
    Activations Density 0.039%

    No Known Activations