© 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. 104717
    Prev
    Next
    INDEX
    Explanations

    being called out

    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
     delo
    -0.89
     oba
    -0.85
    יוון
    -0.84
    tauscht
    -0.83
    proble
    -0.82
    运作
    -0.82
     готовы
    -0.81
    payee
    -0.81
    レッド
    -0.81
     montée
    -0.81
    POSITIVE LOGITS
     being
    1.03
     essere
    1.01
    突然
    0.94
    ถูก
    0.88
    ிய
    0.86
     своему
    0.85
     suddenly
    0.84
     receive
    0.83
    被人
    0.83
     ถูก
    0.80
    Activations Density 0.050%

    No Known Activations