© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49799
    Prev
    Next
    INDEX
    Explanations

    LICENSE file

    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_34/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
    Таблица
    -0.77
     sosial
    -0.71
    扭
    -0.70
    电力
    -0.70
    ди
    -0.70
    髖
    -0.70
    ә
    -0.70
    Gor
    -0.68
    Nid
    -0.68
     recreated
    -0.67
    POSITIVE LOGITS
     päivä
    0.89
     utford
    0.86
    ştir
    0.84
     this
    0.84
    omorphology
    0.83
     arī
    0.82
     genellikle
    0.82
    tahui
    0.82
     via
    0.82
     būti
    0.82
    Activations Density 0.002%

    No Known Activations