© 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. 15726
    Prev
    Next
    INDEX
    Explanations

    download the software

    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
    Ⓖ
    -1.02
    onas
    -0.98
     обратно
    -0.94
     rover
    -0.93
     livelihood
    -0.91
    napp
    -0.87
    ilever
    -0.86
    踝
    -0.85
     {%
    -0.84
    箓
    -0.84
    POSITIVE LOGITS
     today
    1.05
    今日
    0.95
    打量
    0.88
    unjukkan
    0.88
     Auffassung
    0.85
    Judges
    0.84
     is
    0.84
    Calli
    0.84
     कोण
    0.83
     what
    0.83
    Activations Density 0.003%

    No Known Activations