© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54511
    Prev
    Next
    INDEX
    Explanations

    code file paths and licenses

    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
    orul
    -0.97
    ORUS
    -0.91
     coment
    -0.90
    了出去
    -0.88
    tette
    -0.88
    ǽ
    -0.87
    欤
    -0.86
     governo
    -0.85
     biling
    -0.85
     último
    -0.84
    POSITIVE LOGITS
     ajudam
    0.93
     possuem
    0.89
     mortos
    0.87
     atualmente
    0.85
     mães
    0.85
     öns
    0.84
    работки
    0.84
    crito
    0.83
    <%
    0.82
    habhar
    0.82
    Activations Density 0.002%

    No Known Activations