© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71491
    Prev
    Next
    INDEX
    Explanations

    browse, buy, area, visit, follow

    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
    <eos>
    -1.23
    Geograf
    -1.01
     other
    -0.98
    ctivo
    -0.98
    jando
    -0.95
    vierten
    -0.95
     like
    -0.94
    itados
    -0.94
    โคร
    -0.92
    ására
    -0.92
    POSITIVE LOGITS
     nuevos
    0.96
     tutaj
    0.94
    的是
    0.93
    只是
    0.93
     schuhe
    0.92
     nazwa
    0.91
     лучшие
    0.91
    Ie
    0.90
     größe
    0.90
     وأ
    0.89
    Activations Density 0.017%

    No Known Activations