© 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. 75136
    Prev
    Next
    INDEX
    Explanations

    application programming interface

    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
     who
    -1.10
     obsahuje
    -1.05
     Malgré
    -0.90
    を搭載
    -0.89
     personalizadas
    -0.88
     exclusivas
    -0.86
     берегу
    -0.85
     takeaway
    -0.84
     Même
    -0.84
    Kamu
    -0.84
    POSITIVE LOGITS
     of
    0.94
    cieli
    0.91
     eerie
    0.91
    ーンズ
    0.88
    😌
    0.87
    CID
    0.85
     εικό
    0.83
    😝
    0.83
     minOccurs
    0.82
    まさ
    0.82
    Activations Density 0.001%

    No Known Activations